Instructions to use Winst/cross-encoder-ru with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Winst/cross-encoder-ru with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Winst/cross-encoder-ru")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Winst/cross-encoder-ru") model = AutoModel.from_pretrained("Winst/cross-encoder-ru", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model.pt from Winst/cross-encoder-ru: direct link, hf CLI and curl.
- Browser
- Download file 25.2 MB
-
https://huggingface.co/Winst/cross-encoder-ru/resolve/main/model.pt
- Command line
-
hf download hf://Winst/cross-encoder-ru/model.pt
-
curl -L -o model.pt https://huggingface.co/Winst/cross-encoder-ru/resolve/main/model.pt
25.2 MB
- Xet hash:
- 54c2f389f653d01b7504eaee5c22f206600faf4f4abcb1e4471c0c1b3f29405d
- Size of remote file:
- 25.2 MB
- SHA256:
- 217f33df9f8a032ed7c68d00683b84821059a8438456270b1af3e4b42183e6a8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.