---
license: apache-2.0
datasets:
- glue
language:
- en
metrics:
- f1
- accuracy
tags:
- dummy
- language
- paraphrasing
---

# Dummy Model based on BERT (uncased)

This is a fine-tuned version of [`bert-base-uncased`](https://huggingface.co/bert-base-uncased) for detecting whether two sentences are paraphrases.
Following the [HuggingFace course](https://huggingface.co/learn/nlp-course/chapter3/3?fw=pt).

## Model description

Pretty much the same as the original BERT: https://huggingface.co/bert-base-uncased
With a new head, fine-tuned for paraphrasing.

## Intended uses & limitations

Intended use: None. This is just a test :)
Limitations: Idk

## How to use

```python
from transformers import pipeline

pipe = pipeline("text-classification", model="stefanbschneider/bert-base-uncased-dummy")
sentence1 = 'Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .'
sentence2 = 'Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .'
pipe([sentence1, sentence2])
```