Camembert Fr Covid Tweet Classification

🚀 camembert-fr-covid-tweet-classification

This model is designed for tweet classification related to COVID-19 in French. It fine-tunes a checkpoint from Yanzhu/bertweetfr-base on the SST-2 dataset, achieving an accuracy of 66.00% on the dev set.

🚀 Quick Start

This model is a fine - tuned checkpoint of Yanzhu/bertweetfr-base, optimized on the SST - 2 dataset. It attains an accuracy of 66.00% on the development set.

In this dataset, when given a tweet, the objective is to infer the tweet's underlying topic by selecting from four topic classes:

• chiffres: This indicates that the tweet discusses COVID - 19 statistics.
• mesures: This means the tweet talks about the government's COVID - 19 measures.
• opinions: This implies the tweet expresses people's opinions, such as about fake news.
• symptomes: This shows the tweet is about COVID - 19 symptoms or variants.
• divers: Or other topics.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("Monsia/camembert-fr-covid-tweet-classification")
model = AutoModelForSequenceClassification.from_pretrained("Monsia/camembert-fr-covid-tweet-classification")
nlp_topic_classif = transformers.pipeline('topics-classification', model = model, tokenizer = tokenizer)
nlp_topic_classif("tchai on est morts. on va se faire vacciner et ils vont contrôler comme les marionnettes avec des fils. d'après les '' ont dit ''...")
# Output: [{'label': 'opinions', 'score': 0.831]

📄 License

The model is licensed under the Apache - 2.0 license.