How to use nlp-project-uw/quant_1_58b_impl_OneBit_loss_KL with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nlp-project-uw/quant_1_58b_impl_OneBit_loss_KL", device_map="auto")
SFconvertbot commited on 
