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/backends/actioncodec2/sparse/__init__.py from ZibinDong/ActionCodec2: direct link, hf CLI and curl.
- Browser
- Download file 698 Bytes
-
https://huggingface.co/ZibinDong/ActionCodec2/resolve/main/runtime/backends/actioncodec2/sparse/__init__.py
- Command line
-
hf download hf://ZibinDong/ActionCodec2/runtime/backends/actioncodec2/sparse/__init__.py
-
curl -L -o __init__.py https://huggingface.co/ZibinDong/ActionCodec2/resolve/main/runtime/backends/actioncodec2/sparse/__init__.py
698 Bytes
| """ActionCodec2Sparse: ActionCodec2 physics with a zero-free spatio-temporal Set-BPE token layer.""" | |
| from .fitting import SparseProfileTrainer, sparse_profile_config | |
| from .grammar import SparseGrammar | |
| from .layout import SparseLayout | |
| from .processor import ActionCodec2SparseProcessor | |
| from .routing import ActionCodec2SparseRouter, RoutedSparseGrammar | |
| from .training import fit_sparse_vocabulary | |
| from .vocabulary import SparseVocabulary | |
| __all__ = [ | |
| "ActionCodec2SparseProcessor", | |
| "ActionCodec2SparseRouter", | |
| "RoutedSparseGrammar", | |
| "SparseGrammar", | |
| "SparseLayout", | |
| "SparseProfileTrainer", | |
| "SparseVocabulary", | |
| "fit_sparse_vocabulary", | |
| "sparse_profile_config", | |
| ] | |