This model is a fine-tune checkpoint of Yanzhu/bertweetfr-base, fine-tuned on SST-2. This model reaches an accuracy of 71% on the dev set. In this dataset, given a tweet, the goal was to infer the underlying topic of the tweet by choosing from four topics classes:
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("data354/camembert-fr-covid-tweet-sentiment-classification")
model = AutoModelForSequenceClassification.from_pretrained("data354/camembert-fr-covid-tweet-sentiment-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]