metadata
license: mit
tags:
- robotics
- vision-language-action
- robot-manipulation
libero_object
Model Description
This is a vision-language-action model for robotic manipulation with progress-aware spatial subtask planning.
Usage
from transformers import AutoModelForCausalLM, AutoProcessor
model = AutoModelForCausalLM.from_pretrained("SPRVLA/libero_object")
processor = AutoProcessor.from_pretrained("SPRVLA/libero_object")
License
MIT License