Falconss1
VideoThinker-R1-3B
Based on Qwen/Qwen2.5-VL-3B-Instruct
Tags
- safetensors
- qwen2_5_vl
- image-text-to-text
- video-understanding
- reasoning
- multimodal
- reinforcement-learning
- question-answering
- en
- dataset:CLEVRER
- dataset:MMVU
- dataset:Video-Holmes
Languages
en
- Author
- Falconss1
- Task
- video-text-to-text
- Library
- transformers
- Architecture
- qwen2_5_vl
- License
- mit
- Base model
- Qwen/Qwen2.5-VL-3B-Instruct
- Downloads
- 20
- Likes
- 2