Instructions to use BeingBeyond/Being-H0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BeingBeyond/Being-H0 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("BeingBeyond/Being-H0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -131,18 +131,6 @@ python -m beingvla.models.motion.m2m.aligner.eval_policy \
|
|
| 131 |
--action-chunk-length 16
|
| 132 |
```
|
| 133 |
|
| 134 |
-
## TODO
|
| 135 |
-
|
| 136 |
-
The following features are planned for future implementation:
|
| 137 |
-
|
| 138 |
-
- [ ] Real-robot development.
|
| 139 |
-
- [ ] Simulation Benchmark.
|
| 140 |
-
- [ ] Training code and scripts.
|
| 141 |
-
- [ ] Hugging Face transformers library version.
|
| 142 |
-
- [x] Detailed documentation for inferencing using custom images.
|
| 143 |
-
- [x] Post-training data.
|
| 144 |
-
- [x] Inference code and scripts.
|
| 145 |
-
|
| 146 |
## Contributing and Building on Being-H0
|
| 147 |
|
| 148 |
We encourage researchers and practitioners to leverage Being-H0 as a foundation for their own creative experiments and applications. Whether you're adapting Being-H0 to new robotic platforms, exploring novel hand manipulation tasks, or extending the model to new domains, our modular codebase is designed to support your innovations. We welcome contributions of all kinds - from bug fixes and documentation improvements to new features and model architectures. By building on Being-H0 together, we can advance the field of dexterous vision-language-action modeling and enable robots to understand and replicate the rich complexity of human hand movements. Join us in making robotic manipulation more intuitive, capable, and accessible to all.
|
|
|
|
| 131 |
--action-chunk-length 16
|
| 132 |
```
|
| 133 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 134 |
## Contributing and Building on Being-H0
|
| 135 |
|
| 136 |
We encourage researchers and practitioners to leverage Being-H0 as a foundation for their own creative experiments and applications. Whether you're adapting Being-H0 to new robotic platforms, exploring novel hand manipulation tasks, or extending the model to new domains, our modular codebase is designed to support your innovations. We welcome contributions of all kinds - from bug fixes and documentation improvements to new features and model architectures. By building on Being-H0 together, we can advance the field of dexterous vision-language-action modeling and enable robots to understand and replicate the rich complexity of human hand movements. Join us in making robotic manipulation more intuitive, capable, and accessible to all.
|