初始化项目，由ModelHub XC社区提供模型

Model: UCSC-VLAA/MedVLThinker-7B-RL_PMC Source: Original Platform
2026-09-07 16:56:14 +08:00
commit cf6eba1ff3
18 changed files with 1291 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,109 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+tags:
+- vision-language
+- medical
+- multimodal
+- qwen2.5-vl
+datasets:
+- UCSC-VLAA/MedVLThinker-pmc_vqa-gpt_4o_reasoning-tokenized
+- UCSC-VLAA/MedVLThinker-m23k-tokenized
+- UCSC-VLAA/MedVLThinker-pmc_vqa
+- UCSC-VLAA/MedVLThinker-Eval
+language:
+- en
+pipeline_tag: image-text-to-text
+---
+
+# MedVLThinker-7B-RL_PMC
+
+Code: https://github.com/UCSC-VLAA/MedVLThinker
+Project Page: https://ucsc-vlaa.github.io/MedVLThinker/
+
+## Model Description
+
+MedVLThinker-7B-RL_PMC is a 7B parameter medical vision-language model based on Qwen2.5-VL. 
+This model has been trained using reinforcement learning on PMC-VQA dataset.
+
+## Model Details
+
+- **Base Model**: Qwen/Qwen2.5-VL-7B-Instruct
+- **Model Size**: 7B parameters
+- **Training Method**: Reinforcement Learning
+- **Training Data**: PMC-VQA dataset
+
+## Usage
+
+Check here for demo images: https://github.com/UCSC-VLAA/MedVLThinker?tab=readme-ov-file#demo
+
+```python
+from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
+from qwen_vl_utils import process_vision_info
+import torch
+
+# Load the model
+model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+    "UCSC-VLAA/MedVLThinker-7B-RL_PMC",
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+processor = AutoProcessor.from_pretrained("UCSC-VLAA/MedVLThinker-7B-RL_PMC")
+
+# Example usage
+messages = [
+    {
+        "role": "system",
+        "content": "You will solve a problem/request. You should provide your thoughts within <think> </think> tags before providing the answer. Write your final answer within <answer> </answer> tags.",
+    },
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "path/to/medical/image.jpg",
+            },
+            {"type": "text", "text": "What can you see in this medical image?"},
+        ],
+    }
+]
+
+# Preparation for inference
+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")
+
+# Inference
+generated_ids = model.generate(**inputs, max_new_tokens=2048, temperature=0.6, top_p=0.95, do_sample=True)
+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)
+```
+
+## Citation
+
+```bibtex
+@article{medvlthinker2025,
+  title={MedVLThinker: Simple Baselines for Multimodal Medical Reasoning},
+  author={Huang, Xiaoke and Wu, Juncheng and Liu, Hui and Tang, Xianfeng and Zhou, Yuyin},
+  journal={arXiv preprint},
+  year={2025}
+}
+```
+
+## License
+
+This model is released under the Apache 2.0 license.