Instructions to use ynFeng/approximate-speculative-decoding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ynFeng/approximate-speculative-decoding with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ynFeng/approximate-speculative-decoding", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download custom_generate/requirements.txt from ynFeng/approximate-speculative-decoding: direct link, hf CLI and curl.
- Browser
- Download file 187 Bytes
-
https://huggingface.co/ynFeng/approximate-speculative-decoding/resolve/main/custom_generate/requirements.txt
- Command line
-
hf download hf://ynFeng/approximate-speculative-decoding/custom_generate/requirements.txt
-
curl -L -o requirements.txt https://huggingface.co/ynFeng/approximate-speculative-decoding/resolve/main/custom_generate/requirements.txt
187 Bytes
| # The acceptance loop mirrors `GenerationMixin._assisted_decoding` internals, | |
| # so the minor version is pinned. Verified on transformers 5.19.0. | |
| transformers>=5.19.0,<5.20.0 | |
| torch>=2.0.0 | |