Text Classification
Transformers
Safetensors
bert
next-sentence-prediction
easyfhe
mrpc
homomorphic-encryption
Instructions to use jizhuoran/easyfhe-thor-mrpc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jizhuoran/easyfhe-thor-mrpc with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="jizhuoran/easyfhe-thor-mrpc")# Load model directly from transformers import AutoTokenizer, AutoModelForNextSentencePrediction tokenizer = AutoTokenizer.from_pretrained("jizhuoran/easyfhe-thor-mrpc") model = AutoModelForNextSentencePrediction.from_pretrained("jizhuoran/easyfhe-thor-mrpc", device_map="auto") - Notebooks
- Google Colab
- Kaggle
EasyFHE THOR MRPC assets
This repository stores the BERT-base MRPC checkpoint and tokenizer files used by the canonical EasyFHE u64 THOR encrypted-inference example.
model.safetensors: 201 tensors, SHA-2561a9d5a7e7afc705b74820f47d9c1e884b266037ebaa891cfd2474758ce5ccc3dconfig.json: BERT-base next-sentence-prediction configurationvocab.txtandtokenizer_config.json: matching uncased BERT tokenizer
The example uses the glue / mrpc dataset hosted on Hugging Face and pins a
specific dataset revision for reproducibility. The encrypted graph validates
the exact tensor schema before generating FHE keys.
- Downloads last month
- 14
Model tree for jizhuoran/easyfhe-thor-mrpc
Base model
google-bert/bert-base-uncased