Instructions to use nlp-project-uw/quant_1_58b_impl_OneBit_loss_Wasserstein 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_Wasserstein with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nlp-project-uw/quant_1_58b_impl_OneBit_loss_Wasserstein", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from nlp-project-uw/quant_1_58b_impl_OneBit_loss_Wasserstein: direct link, hf CLI and curl.
- Browser
- Download file 256 Bytes
-
https://huggingface.co/nlp-project-uw/quant_1_58b_impl_OneBit_loss_Wasserstein/resolve/main/config.json
- Command line
-
hf download hf://nlp-project-uw/quant_1_58b_impl_OneBit_loss_Wasserstein/config.json
-
curl -L -o config.json https://huggingface.co/nlp-project-uw/quant_1_58b_impl_OneBit_loss_Wasserstein/resolve/main/config.json
256 Bytes
| { | |
| "architectures": [ | |
| "HFQuantizedSmolModel" | |
| ], | |
| "bitlinear_implementation": "OneBit", | |
| "loss_function": "Wasserstein", | |
| "model_type": "quantized_net42", | |
| "quantization": "1_58b", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.52.4" | |
| } | |