Instructions to use nlp-project-uw/quant_1b_impl_BitNet_loss_CrossEntropy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nlp-project-uw/quant_1b_impl_BitNet_loss_CrossEntropy with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nlp-project-uw/quant_1b_impl_BitNet_loss_CrossEntropy", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from nlp-project-uw/quant_1b_impl_BitNet_loss_CrossEntropy: direct link, hf CLI and curl.
- Browser
- Download file 539 MB
-
https://huggingface.co/nlp-project-uw/quant_1b_impl_BitNet_loss_CrossEntropy/resolve/refs%2Fpr%2F2/pytorch_model.bin
- Command line
-
hf download hf://nlp-project-uw/quant_1b_impl_BitNet_loss_CrossEntropy@refs/pr/2/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/nlp-project-uw/quant_1b_impl_BitNet_loss_CrossEntropy/resolve/refs%2Fpr%2F2/pytorch_model.bin
539 MB
- Xet hash:
- aad4962003392735cad781e2db49d5a1f6a90ee4b76fd31f5545028f1433f182
- Size of remote file:
- 539 MB
- SHA256:
- 51ff9ea8d46cea0aa52aa2cd838005c8cee9c554cc06a020d30131256d3f6214
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.