metadata
license: apache-2.0
datasets:
- Video-R1/Video-R1-data
language:
- en
base_model:
- Qwen/Qwen2.5-7B-Instruct
The SFT cold start model trained by the Video-R1-COT-165k dataset.
This intermediate checkpoint can be used as the base model for RL training on the Video-R1-260k dataset.
Please refer to: https://github.com/tulerfeng/Video-R1