gme-Qwen2-VL-7B-Instruct

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]

from transformers import AutoModel
from transformers.utils.versions import require_version


require_version(
    "transformers<4.52.0",
    "The remote code has some issues with transformers>=4.52.0, please downgrade: pip install transformers==4.51.3"
)


t2i_prompt = 'Find an image that matches the given text.'
texts = [
    "The Tesla Cybertruck is a battery electric pickup truck built by Tesla, Inc. since 2023.",
    "Alibaba office.",
]
images = [
    'https://upload.wikimedia.org/wikipedia/commons/e/e9/Tesla_Cybertruck_damaged_window.jpg',
    'https://upload.wikimedia.org/wikipedia/commons/e/e0/TaobaoCity_Alibaba_Xixi_Park.jpg',
]


gme = AutoModel.from_pretrained(
    "Alibaba-NLP/gme-Qwen2-VL-7B-Instruct",
    torch_dtype="float16", device_map='cuda', trust_remote_code=True
)


# Single-modal embedding
e_text = gme.get_text_embeddings(texts=texts)
e_image = gme.get_image_embeddings(images=images)
print('Single-modal', (e_text @ e_image.T).tolist())
## Single-modal [[0.279296875, 0.0002658367156982422], [0.06427001953125, 0.304443359375]]

# How to set embedding instruction
e_query = gme.get_text_embeddings(texts=texts, instruction=t2i_prompt)
# If is_query=False, we always use the default instruction.
e_corpus = gme.get_image_embeddings(images=images, is_query=False)
print('Single-modal with instruction', (e_query @ e_corpus.T).tolist())
## Single-modal with instruction [[0.32861328125, 0.026336669921875], [0.09466552734375, 0.3134765625]]

# Fused-modal embedding
e_fused = gme.get_fused_embeddings(texts=texts, images=images)
print('Fused-modal', (e_fused @ e_fused.T).tolist())
## Fused-modal [[1.0, 0.0308685302734375], [0.0308685302734375, 1.0]]