Instructions to use ZibinDong/ActionCodec2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ZibinDong/ActionCodec2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ZibinDong/ActionCodec2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download runtime/frontend/actioncodec2/__init__.py from ZibinDong/ActionCodec2: direct link, hf CLI and curl.
- Browser
- Download file 585 Bytes
-
https://huggingface.co/ZibinDong/ActionCodec2/resolve/main/runtime/frontend/actioncodec2/__init__.py
- Command line
-
hf download hf://ZibinDong/ActionCodec2/runtime/frontend/actioncodec2/__init__.py
-
curl -L -o __init__.py https://huggingface.co/ZibinDong/ActionCodec2/resolve/main/runtime/frontend/actioncodec2/__init__.py
585 Bytes
| """Arbitrary-horizon frontend bound to one ActionCodec2 action space.""" | |
| from transformers import AutoConfig, AutoProcessor | |
| from ...backends.actioncodec2.hf import ActionCodec2FrontendHFConfig | |
| from .generation import ActionCodec2LogitsProcessor | |
| from .processor import ActionCodec2 | |
| from .tokenizer import ActionCodec2Tokenizer | |
| AutoConfig.register(ActionCodec2.model_type, ActionCodec2FrontendHFConfig, exist_ok=True) | |
| AutoProcessor.register(ActionCodec2FrontendHFConfig, ActionCodec2, exist_ok=True) | |
| __all__ = ["ActionCodec2", "ActionCodec2Tokenizer", "ActionCodec2LogitsProcessor"] | |