|
|
--- |
|
|
license: cc-by-nc-4.0 |
|
|
language: |
|
|
- en |
|
|
tags: |
|
|
- English |
|
|
- Bert-base |
|
|
- Text Classification |
|
|
pipeline_tag: text-classification |
|
|
--- |
|
|
|
|
|
# RoBERTa base Fine-Tuned for Proposal Sentence Classification |
|
|
|
|
|
## Overview |
|
|
|
|
|
- **Language**: English |
|
|
- **Model Name**: oeg/BERT-Repository-Proposal |
|
|
|
|
|
## Description |
|
|
|
|
|
This model is a fine-tuned bert base uncased model trained to classify sentences into two classes: proposal and non-proposal sentences. The training data includes sentences proposing a software or data repository. The model is trained to recognize and classify these sentences accurately. |
|
|
|
|
|
## How to use |
|
|
|
|
|
To use this model in Python: |
|
|
|
|
|
```python |
|
|
from transformers import RobertaForSequenceClassification, RobertaTokenizer |
|
|
import torch |
|
|
|
|
|
tokenizer = RobertaTokenizer.from_pretrained("bert-repo-proposal-tokenizer") |
|
|
model = RobertaForSequenceClassification.from_pretrained("bert-repo-proposal-model") |
|
|
|
|
|
sentence = "Your input sentence here." |
|
|
inputs = tokenizer(sentence, return_tensors="pt") |
|
|
outputs = model(**inputs) |
|
|
probabilities = torch.nn.functional.softmax(outputs.logits, dim=1) |
|
|
|
