LLaRA Model Card
This model is released with paper LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
Xiang Li1, Cristina Mata1, Jongwoo Park1, Kumara Kahatapitiya1, Yoo Sung Jang1, Jinghuan Shang1, Kanchana Ranasinghe1, Ryan Burgert1, Mu Cai2, Yong Jae Lee2, and Michael S. Ryoo1
1Stony Brook University 2University of Wisconsin-Madison
Model details
Model type:
LLaRA is an open-source visuomotor policy trained by fine-tuning LLaVA-7b-v1.5 on instruction-following data D-inBC
and 6 auxiliary datasets, converted from VIMA-Data.
For the conversion code, please refer to convert_vima.ipynb
Model date: llava-1.5-7b-llara-D-inBC-Aux-D-VIMA-80k was trained in June 2024.
Paper or resources for more information: https://github.com/LostXine/LLaRA
Where to send questions or comments about the model: https://github.com/LostXine/LLaRA/issues
Intended use
Primary intended uses: The primary use of LLaRA is research on large multimodal models for robotics.
Primary intended users: The primary intended users of the model are researchers and hobbyists in robotics, computer vision, natural language processing, machine learning, and artificial intelligence.
- Downloads last month
- 18