Instructions to use nlp-project-uw/quant_1_58b_impl_OneBit_loss_CAKL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nlp-project-uw/quant_1_58b_impl_OneBit_loss_CAKL with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nlp-project-uw/quant_1_58b_impl_OneBit_loss_CAKL", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 80f3b8186dd0d18f04d8b502b15908a91aed3470ad4e1b240c50a527f6e954fb
- Size of remote file:
- 539 MB
- SHA256:
- be5abb6eaa680ba5f2aae3efcb4f23ed3bdf93ef0db26b43fe9d9f27974689cf
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.