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