---
language: fr
license: mit
datasets:
- amazon_reviews_multi
- allocine
widget:
- text: "Je pensais lire un livre nul, mais finalement je l'ai trouvé super..."
---

DistilCamemBERT-Sentiment
=========================

We present DistilCamemBERT-Sentiment which is [DistilCamemBERT](https://huggingface.co/cmarkea/distilcamembert-base) fine tuned for the sentiment analysis task for the French language. This model is construct over 2 datasets: [Amazon Reviews](https://huggingface.co/datasets/amazon_reviews_multi) and [Allociné.fr](https://huggingface.co/datasets/allocine) to aims minimize the biais. Inded, Amazon review are very similare beetwen the messages and relatevely short, to opposate Allocine criticims are long and rich text.

This modelisation is closely of [tblard/tf-allocine](https://huggingface.co/tblard/tf-allocine) base on [CamemBERT](https://huggingface.co/camembert-base) model. The problem of the modelizations based on CamemBERT is at the scaling moment, for the production phase for example. Indeed, inference cost can be a technological issue. To counteract this effect, we propose this modelization which **divides the inference time by 2** with the same consumption power thanks to [DistilCamemBERT](https://huggingface.co/cmarkea/distilcamembert-base).

Dataset
-------
 
Evaluation results
------------------

Benchmark
---------

How to use DistilCamemBERT-Sentiment
------------------------------------