---

language: 
- fr
tags:
- fr

---
### Best french QA model shared on HF!
It also has a great unique feature : it will output a low probability  if the answer is not in the context!

( Depending on the sensibility of your use case, you will choose a threshold under which the answer should be rejected.)


### FQuAD Evaluation
```shell
{'exact_match': 57.214554579673774, 'f1': 80.75789384679857}''
```

## Usage

```python
from transformers import pipeline

nlp = pipeline('question-answering', model='CATIE-AQ/camembert_v2.0', tokenizer='CATIE-AQ/camembert_v2.0')

nlp({
    'question': "Qui est Claude Monet?",
    'context': "Claude Monet, né le 14 novembre 1840 à Paris et mort le 5 décembre 1926 à Giverny, est un peintre français et l’un des fondateurs de l'impressionnisme."
})
```
```python
{'score': 0.19230681657791138,
 'start': 20,
 'end': 36,
 'answer': 'un peintre français'}
```

This model was trained on our servers with several datasets :
- fquad
- squad2fr (traduction from squad2 de pragnakalp)
- piaf 1.0+1.1+1.2
- newsquadfr
- one dataset of ours of squad v2.0 type, the answer is NOT in the context.



The CATIE (Centre Aquitain des Technologies de l'Information et Électroniques) is a center for technologic transfer specialized in digital technologies. 
CATIE has a multidisciplinary approach through three fields of action : human factors and cognition, digital systems and AI.
https://www.catie.fr/en/home/