lee31221
VITA-RL
Based on VITA-MLLM/VITA-1.5
Tags
- safetensors
- lora
- grpo
- dpo
- multimodal
- vita
- base_model:VITA-MLLM/VITA-1.5
- base_model:adapter:VITA-MLLM/VITA-1.5
- license:apache-2.0
- region:us
- Author
- lee31221
- Task
- reinforcement-learning
- License
- apache-2.0
- Base model
- VITA-MLLM/VITA-1.5
- Downloads
- 0
- Likes
- 0
