Instructions to use JLake310/bert-p-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JLake310/bert-p-encoder with Transformers:
# Load model directly from transformers import AutoTokenizer, HFBertEncoder tokenizer = AutoTokenizer.from_pretrained("JLake310/bert-p-encoder") model = HFBertEncoder.from_pretrained("JLake310/bert-p-encoder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from JLake310/bert-p-encoder: direct link, hf CLI and curl.
- Browser
- Download file 443 MB
-
https://huggingface.co/JLake310/bert-p-encoder/resolve/refs%2Fpr%2F1/pytorch_model.bin
- Command line
-
hf download hf://JLake310/bert-p-encoder@refs/pr/1/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/JLake310/bert-p-encoder/resolve/refs%2Fpr%2F1/pytorch_model.bin
443 MB
- Xet hash:
- c42660149a650c6b72fb906ab224bfb9b4d5f64e5a9db9965fbc539e7d53229e
- Size of remote file:
- 443 MB
- SHA256:
- 5b9e2b7395b2ae445c9369a17a959fc641df6a079e018e9e7483a05381c24e2b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.