Overview
OpenVLThinker-7B is a vision-language reasoning model designed to handle multimodal tasks. It is especially tuned for visual mathematical problem-solving.
For more details: Blog, GitHub
How to use
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
import torch
from qwen_vl_utils import process_vision_info
import requests
from PIL import Image
# 1. Define model and processor names
model_name = "ydeng9/OpenVLThinker-7B"
processor_name = "Qwen/Qwen2.5-VL-7B-Instruct"
# 2. Load the OpenVLThinker-7B model and processor
device = "cuda:0" if torch.cuda.is_available() else "cpu"
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
attn_implementation="flash_attention_2",
device_map=device
)
processor = AutoProcessor.from_pretrained(processor_name)
# 3. Define a sample image URL and an instruction
image_url = "https://example.com/sample_image.jpg" # replace with your image URL
instruction = "Example question"
# 4. Create a multimodal prompt using a chat message structure
messages = [
{
"role": "user",
"content": [
{"type": "image", "image": image_url},
{"type": "text", "text": instruction},
],
}
]
# 5. Generate a text prompt from the chat messages
text_prompt = processor.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
# 6. Process image (and video) inputs from the messages
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
text=[text_prompt],
images=image_inputs,
videos=video_inputs,
padding=True,
return_tensors="pt",
).to(device)
# 7. Generate the model's response (with specified generation parameters)
generated_ids = model.generate(
**inputs,
do_sample=True,
max_new_tokens=2048,
top_p=0.001,
top_k=1,
temperature=0.01,
repetition_penalty=1.0,
)
# 8. Decode the generated tokens into human-readable text
generated_text = processor.batch_decode(
generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)[0]
# 9. Print the generated response
print("Generated Response:")
print(generated_text)
Citation
@misc{deng2025openvlthinker,
title={OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement},
author={Yihe Deng and Hritik Bansal and Fan Yin and Nanyun Peng and Wei Wang and Kai-Wei Chang},
year={2025},
eprint={2503.17352},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2503.17352},
}