初始化项目，由ModelHub XC社区提供模型

Model: OpenGVLab/VideoChat-R1_7B_caption
Source: Original Platform

README.md

@@ -0,0 +1,100 @@
+---
+language:
+- en
+library_name: transformers
+license: apache-2.0
+metrics:
+- accuracy
+tags:
+- multimodal
+pipeline_tag: video-text-to-text
+base_model: Qwen/Qwen2-VL-7B-Instruct
+---
+
+
+# 💡 VideoChat-R1_7B_caption
+
+[\[📂 GitHub\]](https://github.com/OpenGVLab/VideoChat-R1)  
+[\[📜 Tech Report\]](https://arxiv.org/pdf/2504.06958) 
+
+
+## 🚀 How to use the model
+
+We provide a simple installation example below:
+```
+pip install transformers
+pip install qwen_vl_utils
+```
+Then you could use our model:
+```python
+from transformers import Qwen2_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
+from qwen_vl_utils import process_vision_info
+
+model_path = "OpenGVLab/VideoChat-R1_7B_caption"
+# default: Load the model on the available device(s)
+model = Qwen2_VLForConditionalGeneration.from_pretrained(
+    model_path, torch_dtype="auto", device_map="auto",
+    attn_implementation="flash_attention_2"
+)
+
+# default processer
+processor = AutoProcessor.from_pretrained(model_path)
+
+video_path = "your_video.mp4"
+question = "Describe the video in detail."
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "video",
+                "video": video_path,
+                "max_pixels": 360 * 420,
+                "fps": 1.0,
+            },
+            {"type": "text", "text": f""""{question} First output the thinking process in <think> </think> tags and then output the final answer in <answer> </answer> tags"""},
+        ],
+    }
+]
+
+
+
+#In Qwen 2 VL, frame rate information is also input into the model to align with absolute time.
+# Preparation for inference
+text = processor.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True)
+inputs = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+    **video_kwargs,
+)
+inputs = inputs.to("cuda")
+
+# Inference
+generated_ids = model.generate(**inputs, max_new_tokens=512)
+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{li2025videochatr1,
+  title={VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning},
+  author={Li, Xinhao and Yan, Ziang and Meng, Desen and Dong, Lu and Zeng, Xiangyu and He, Yinan and Wang, Yali and Qiao, Yu and Wang, Yi and Wang, Limin},
+  journal={arXiv preprint arXiv:2504.06958},
+  year={2025}
+}
+```