metadata
license: apache-2.0
datasets:
- Video-R1/Video-R1-data
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
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