Improve model card: Add pipeline tag, library name, paper link, authors, and sample usage

This PR significantly enhances the model card for `Video-R1/Qwen2.5-VL-7B-COT-SFT` by:

- Adding the `pipeline_tag: video-text-to-text` to ensure proper categorization and discoverability on the Hugging Face Hub.
- Specifying `library_name: transformers`, enabling direct integration and a "how to use" widget for the model with the 🤗 Transformers library, supported by `config.json` evidence.
- Adding an explicit link to the official paper on Hugging Face Papers.
- Including the list of authors for proper attribution.
- Expanding the model description with an "About" section based on the paper's abstract.
- Providing a clear `transformers`-based code snippet for sample inference.

These improvements will make the model more accessible, informative, and user-friendly for the community.

README.md

@@ -1,15 +1,96 @@
 ---
-license: apache-2.0
+base_model:
+- Qwen/Qwen2.5-7B-Instruct
 datasets:
 - Video-R1/Video-R1-data
 language:
 - en
-base_model:
-- Qwen/Qwen2.5-7B-Instruct
+license: apache-2.0
+pipeline_tag: video-text-to-text
+library_name: transformers
 ---
 
-The SFT cold start model trained by the Video-R1-COT-165k dataset. 
+# Video-R1: Reinforcing Video Reasoning in MLLMs
+
+This repository contains `Video-R1/Qwen2.5-VL-7B-COT-SFT`, the SFT (Supervised Fine-Tuning) cold start model trained using the Video-R1-COT-165k dataset. This intermediate checkpoint serves as the base model for further RL (Reinforcement Learning) training on the Video-R1-260k dataset to produce the final Video-R1 models.
+
+For more details, please refer to the paper: [Video-R1: Reinforcing Video Reasoning in MLLMs](https://huggingface.co/papers/2503.21776).
+The full code and additional resources are available on the [GitHub repository](https://github.com/tulerfeng/Video-R1).
+
+## About Video-R1
+
+Video-R1 represents the first systematic exploration of the R1 paradigm for incentivizing video reasoning within multimodal large language models (MLLMs), inspired by the success of DeepSeek-R1. The project addresses key challenges in video reasoning, particularly the lack of temporal modeling and the scarcity of high-quality video-reasoning data.
+
+To tackle these issues, Video-R1 proposes the T-GRPO algorithm, an extension of GRPO that explicitly encourages models to leverage temporal information in videos for reasoning. It also strategically incorporates high-quality image-reasoning data into the training process. The model was trained on two newly constructed datasets: Video-R1-CoT-165k for SFT cold start and Video-R1-260k for RL training, both comprising image and video data.
+
+Experimental results demonstrate that Video-R1 achieves significant improvements on various video reasoning benchmarks, including VideoMMMU, VSI-Bench, MVBench, and TempCompass. Notably, Video-R1-7B has shown competitive performance, even surpassing proprietary models like GPT-4o on certain video spatial reasoning tasks.
+
+## Authors
+
+-   Kaituo Feng
+-   Kaixiong Gong
+-   Bohao Li
+-   Zonghao Guo
+-   Yibing Wang
+-   Tianshuo Peng
+-   Benyou Wang
+-   Xiangyu Yue
+
+## Sample Usage
+
+We provide a simple generation process for using this SFT cold start model with the `transformers` library.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, AutoProcessor
+from PIL import Image
+import cv2
+from decord import VideoReader, cpu
+
+# Load model, tokenizer, and processor
+model_id = "Video-R1/Qwen2.5-VL-7B-COT-SFT" # This specific SFT checkpoint
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="cuda",
+    trust_remote_code=True,
+)
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
+
+# Function to load video frames
+def load_video_frames(video_path, num_frames=16):
+    vr = VideoReader(video_path, ctx=cpu(0))
+    total_frames = len(vr)
+    indices = [int(i * (total_frames / num_frames)) for i in range(num_frames)]
+    frames = vr.get_batch(indices).asnumpy()
+    frames = [Image.fromarray(frame) for frame in frames]
+    return frames
+
+# Example usage
+# Replace with your actual video path
+# For demonstration, ensure a video file like 'examples/video1.mp4' exists or adjust path
+video_path = "./examples/video1.mp4" 
+frames = load_video_frames(video_path)
+text = "Describe this video in detail."
+
+# Prepare inputs
+inputs = processor(frames=frames, text=text, return_tensors="pt").to("cuda")
+
+# Generate response
+output = model.generate(**inputs, max_new_tokens=50)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
+```
+
+## Citation
 
-This intermediate checkpoint can be used as the base model for RL training on the Video-R1-260k dataset.
+If you find our work helpful for your research, please consider citing our work:
 
-Please refer to: https://github.com/tulerfeng/Video-R1
+```bibtex
+@article{feng2025video,
+  title={Video-R1: Reinforcing Video Reasoning in MLLMs},
+  author={Feng, Kaituo and Gong, Kaixiong and Li, Bohao and Guo, Zonghao and Wang, Yibing and Peng, Tianshuo and Wang, Benyou and Yue, Xiangyu},
+  journal={arXiv preprint arXiv:2503.21776},
+  year={2025}
+}
+```