https://github.com/brianhuster/mrpc-bert
a Bert-based language model used to recognize if 2 English sentences are equivalent in meaning
https://github.com/brianhuster/mrpc-bert
Last synced: over 1 year ago
JSON representation
a Bert-based language model used to recognize if 2 English sentences are equivalent in meaning
- Host: GitHub
- URL: https://github.com/brianhuster/mrpc-bert
- Owner: brianhuster
- Created: 2024-03-26T11:22:44.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-04-22T04:16:01.000Z (over 2 years ago)
- Last Synced: 2025-03-16T01:22:31.803Z (over 1 year ago)
- Language: Jupyter Notebook
- Size: 20.5 KB
- Stars: 4
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MRPC-bert
This language model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE MRPC dataset.
Model link : [https://huggingface.co/brianhuster/MRPC-bert/](https://huggingface.co/brianhuster/MRPC-bert/)
### Training hyperparameters
The following hyperparameters were used during training:
- num_epochs: 3
### Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.0
#Running model with Python
```
from transformers import pipeline
classifier = pipeline("text-classification", model="brianhuster/MRPC-bert")
classifier(
"Sentence 1. Sentence 2."
)
```
Replace "Sentence 1" and "Sentence 2" with your actual input sentence. Each sentence should end with a fullstop, even if they are questions. The model will return LABEL_1 if they are are equivalent in meaning, LABEL_0 otherwise.