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/_types.py from ZibinDong/ActionCodec2: direct link, hf CLI and curl.
- Browser
- Download file 377 Bytes
-
https://huggingface.co/ZibinDong/ActionCodec2/resolve/main/runtime/frontend/_types.py
- Command line
-
hf download hf://ZibinDong/ActionCodec2/runtime/frontend/_types.py
-
curl -L -o _types.py https://huggingface.co/ZibinDong/ActionCodec2/resolve/main/runtime/frontend/_types.py
377 Bytes
| """Shared lightweight types for the frontend layer.""" | |
| from __future__ import annotations | |
| from typing import NamedTuple | |
| import numpy as np | |
| import torch | |
| ActionIdxBatch = list[list[int]] | |
| TokenIds = list[int] | np.ndarray | torch.Tensor | |
| class DecodeResult(NamedTuple): | |
| action: torch.Tensor | |
| absent_keys: set | |
| __all__ = ["ActionIdxBatch", "TokenIds", "DecodeResult"] | |