Instructions to use McGill-NLP/dpr-statcan-metadata_encoder-basic_info with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use McGill-NLP/dpr-statcan-metadata_encoder-basic_info with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, DPRContextEncoder tokenizer = AutoTokenizer.from_pretrained("McGill-NLP/dpr-statcan-metadata_encoder-basic_info") model = DPRContextEncoder.from_pretrained("McGill-NLP/dpr-statcan-metadata_encoder-basic_info", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from McGill-NLP/dpr-statcan-metadata_encoder-basic_info: direct link, hf CLI and curl.
- Browser
- Download file 438 MB
-
https://huggingface.co/McGill-NLP/dpr-statcan-metadata_encoder-basic_info/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://McGill-NLP/dpr-statcan-metadata_encoder-basic_info/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/McGill-NLP/dpr-statcan-metadata_encoder-basic_info/resolve/main/pytorch_model.bin
438 MB
- Xet hash:
- fe38711c2cdd4f77c44ab888f37d0b38c628f45450a24424ba3333d9a04b2969
- Size of remote file:
- 438 MB
- SHA256:
- 8b440dde142fe8d081d3e11a2550b576eb9c29b86b0758101943708f46d10ea8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.