Instructions to use transformers-community/sink_cache with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use transformers-community/sink_cache with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("transformers-community/sink_cache", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from transformers-community/sink_cache: direct link, hf CLI and curl.
- Browser
- Download file 239 Bytes
-
https://huggingface.co/transformers-community/sink_cache/resolve/refs%2Fpr%2F2/generation_config.json
- Command line
-
hf download hf://transformers-community/sink_cache@refs/pr/2/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/transformers-community/sink_cache/resolve/refs%2Fpr%2F2/generation_config.json
239 Bytes
- Xet hash:
- 8905dd86adca41f8c34e2824020dc08c05340622bfc130098d308f91adaab4d1
- Size of remote file:
- 239 Bytes
- SHA256:
- 2325da0f15bb848e018c5ae071b7943332e9f871d6b60e2ed22ca97d4cb993d2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.