Downloads · 30 days
66
1% of all-time downloads
AgentPublic/camembert-base-toxic-fr-user-prompts
camembert-base-toxic-fr-user-prompts is a text classification model from AgentPublic. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a camembert-base model fine-tuned on a French translated toxic-chat dataset plus additional synthetic data. The model is trained to classify user prompts into three categories: "Toxic", "Non-Toxic", and…
Downloads · 30 days
66
1% of all-time downloads
All-time downloads
5K
Public
Parameters
111M
1.3 GB on disk
Likes
8
Public
Click a slice to open those files.
.safetensors443 MB · 99%
From the Hugging Face model README
This model is a camembert-base model fine-tuned on a French translated toxic-chat dataset plus additional synthetic data. The model is trained to classify user prompts into three categories: "Toxic", "Non-Toxic", and "Sensible".
The evaluation results are as follows (still under evaluation, more data is needed):
| Precision | Recall | F1-Score | |
|---|---|---|---|
| Non-Toxic | 0.97 | 0.95 | 0.96 |
| Sensible | 0.95 | 0.99 | 0.98 |
| Toxic | 0.87 | 0.90 | 0.88 |
| Accuracy | 0.94 | ||
| Macro Avg | 0.93 | 0.95 | 0.94 |
| Weighted Avg | 0.94 | 0.94 | 0.94 |
Note: This model is still under development, and its performance and characteristics are subject to change as training is not yet complete.