fr-naxai-ai-sentiment-classification-234220122023
The model is trained on the sentiment classification task in the French language. It uses 3 labels: -1, 0 and 1. These labels represent negative, neutral and positive sentiments.
This model is finetuned from Distilcamember. A distillation version of the CamemBERT model, a RoBERTa French model version.
Model Details
- Language: fr
- Problem type: Multi-class Classification
- Model Architecture: distilcamembert
- Model Name: fr-naxai-ai-sentiment-classification-234220122023
- Creation date: 23:42h 20/12/2023
Classification Report:
Label | Precision | Recall | f1-Score | Support |
---|---|---|---|---|
-1 | 0.98 | 0.98 | 0.98 | 4117 |
0 | 0.84 | 0.82 | 0.83 | 631 |
1 | 0.96 | 0.97 | 0.97 | 2184 |
accuracy | 0.96 | 6932 | ||
macro avg | 0.93 | 0.92 | 0.03 | 6932 |
weighted avg | 0.96 | 0.96 | 0.96 | 6932 |
How to use this model
You can use Python to access this model:
from transformers import pipeline
analyzer = pipeline(
task='text-classification',
model=“botdevringring/fr-naxai-ai-sentiment-classification-234220122023”,
tokenizer="botdevringring/fr-naxai-ai-sentiment-classification-234220122023"
)
result = analyzer(
"J'aime me promener en forêt même si ça me donne mal aux pieds."
)
result
[
{
'label': '0',
'score': 0.515792965888977
}
]
Or you can use cURL:
curl https://api-inference.huggingface.co/models/botdevringring/fr-naxai-ai-sentiment-classification-234220122023 \
-X POST \
-d '{"inputs": "J'aime me promener en forêt même si ça me donne mal aux pieds."}' \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer <Your HF API token>"
Acknowledgements
Model trained by Eduardo Brigham for Naxai powered by The Ring Ring Company
- Downloads last month
- 9
Evaluation results
- Accuracy on sentimenttest set self-reported0.960
- loss on sentimenttest set self-reported0.337
- Precision Macro on sentimenttest set self-reported0.907
- Precision Micro on sentimenttest set self-reported0.910
- Precision Weighted on sentimenttest set self-reported0.907
- Recall Macro on sentimenttest set self-reported0.828
- Recall Micro on sentimenttest set self-reported0.910
- Recall Weighted on sentimenttest set self-reported0.910
- F1 Macro on sentimenttest set self-reported0.840
- F1 Micro on sentimenttest set self-reported0.910
- F1 Weighted on sentimenttest set self-reported0.908