Imgscope-OCR-2B-0527

111
2
2.0B
1 language
license:apache-2.0
by
prithivMLmods
Image Model
OTHER
2B params
New
111 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
5GB+ RAM
Mobile
Laptop
Server
Quick Summary

> The Imgscope-OCR-2B-0527 model is a fine-tuned version of Qwen2-VL-2B-Instruct, specifically optimized for messy handwriting recognition, document OCR, realis...

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
2GB+ RAM

Code Examples

How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
print(output_text)
How to Usepythontransformers
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Imgscope-OCR-2B-0527",  # replace with updated model ID if available
    torch_dtype="auto",
    device_map="auto"
)

# Optional: Flash Attention for performance optimization
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Imgscope-OCR-2B-0527",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Imgscope-OCR-2B-0527")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Recognize the handwriting in this image."},
        ],
    }
]

# Prepare input
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")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=128)
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
)
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.