Robotics
Transformers
Safetensors
mwm
feature-extraction
vision-language-model
manipulation
custom_code
Instructions to use InternRobotics/F1-VLA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use InternRobotics/F1-VLA with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("InternRobotics/F1-VLA", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update License to MIT, Add Paper Abstract, and Enhance Usage Section
#1
by nielsr HF Staff - opened
This PR updates the model card for F1: A Vision-Language-Action Model to:
- Correct the
licensemetadata and the license section in the Markdown content tomit, aligning with the explicit statement and badge in the official GitHub repository. - Integrate the paper's abstract to provide users with a concise overview of the model directly on the Hugging Face Hub.
- Enhance the "Usage" section by incorporating the detailed "Quick Start" (Prerequisites, Installation, Download, and Finetune example) from the GitHub README, making it easier for users to interact with the model.
- Update the BibTeX citation to the more complete version found in the GitHub README.
No changes were made to the paper link (kept the arXiv link as per instructions), GitHub link, or project page link, as they were already correctly present.