Qwen2-VL-72B-Instruct-abliterated

Name: Qwen2-VL-72B-Instruct-abliterated
Author: huihui-ai

—

huihui-ai

Image Model

OTHER

72B params

New

47 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

161GB+ RAM

Mobile

Laptop

Server

Quick Summary

This is an uncensored version of Qwen2-VL-72B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it).

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

68GB+ RAM

Code Examples

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Usagepythontransformers

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

model = Qwen2VLForConditionalGeneration.from_pretrained(
    "huihui-ai/Qwen2-VL-72B-Instruct-abliterated", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("huihui-ai/Qwen2-VL-72B-Instruct-abliterated")

image_path = "/tmp/test.png"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": f"file://{image_path}",
            },
            {"type": "text", "text": "Please describe the content of the photo in detail"},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
output_text = output_text[0]

print(output_text)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.