Instructions to use HCKLab/BiBert-NSP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HCKLab/BiBert-NSP with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("HCKLab/BiBert-NSP") model = AutoModel.from_pretrained("HCKLab/BiBert-NSP", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from HCKLab/BiBert-NSP: direct link, hf CLI and curl.
- Browser
- Download file 440 MB
-
https://huggingface.co/HCKLab/BiBert-NSP/resolve/refs%2Fpr%2F1/pytorch_model.bin
- Command line
-
hf download hf://HCKLab/BiBert-NSP@refs/pr/1/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/HCKLab/BiBert-NSP/resolve/refs%2Fpr%2F1/pytorch_model.bin
440 MB
- Xet hash:
- 1cf285a4b757d37e62cf06364a9e8af61989fe1385250279eeff39e2ee22345f
- Size of remote file:
- 440 MB
- SHA256:
- eb4160d3b6dea2e959a232475c9e52cd83fc30a66b62ed619cd39e8581a74959
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.