Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ widget:
|
|
| 11 |
example_title: Toxic
|
| 12 |
- text: J'aimerais adopter un chien. Où devrais-je aller ?
|
| 13 |
example_title: Non Toxic
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
This model is a [camembert-base](https://huggingface.co/almanach/camembert-base) model fine-tuned on a French translated [toxic-chat](https://huggingface.co/datasets/lmsys/toxic-chat) dataset. The model is trained to classify user prompts as "Toxic" or "Non-Toxic".
|
| 16 |
|
|
@@ -18,9 +20,10 @@ The evaluation results are as follows:
|
|
| 18 |
|
| 19 |
| | Precision | Recall | F1-Score |
|
| 20 |
|----------------|:-----------:|:---------:|:----------:|
|
| 21 |
-
| **Non-Toxic** | 0.
|
| 22 |
-
| **
|
|
|
|
| 23 |
| | | | |
|
| 24 |
-
| **Accuracy** | | | 0.
|
| 25 |
-
| **Macro Avg** | 0.93 | 0.
|
| 26 |
-
| **Weighted Avg** | 0.
|
|
|
|
| 11 |
example_title: Toxic
|
| 12 |
- text: J'aimerais adopter un chien. Où devrais-je aller ?
|
| 13 |
example_title: Non Toxic
|
| 14 |
+
- text: Comment aider un enfant qui se fait harceler à l'école ?
|
| 15 |
+
example_title: Sensible
|
| 16 |
---
|
| 17 |
This model is a [camembert-base](https://huggingface.co/almanach/camembert-base) model fine-tuned on a French translated [toxic-chat](https://huggingface.co/datasets/lmsys/toxic-chat) dataset. The model is trained to classify user prompts as "Toxic" or "Non-Toxic".
|
| 18 |
|
|
|
|
| 20 |
|
| 21 |
| | Precision | Recall | F1-Score |
|
| 22 |
|----------------|:-----------:|:---------:|:----------:|
|
| 23 |
+
| **Non-Toxic** | 0.96 | 0.91 | 0.93 |
|
| 24 |
+
| **Sensible** | 0.93 | 1.00 | 0.97 |
|
| 25 |
+
| **Toxic** | 0.88 | 0.93 | 0.91 |
|
| 26 |
| | | | |
|
| 27 |
+
| **Accuracy** | | | 0.93 |
|
| 28 |
+
| **Macro Avg** | 0.93 | 0.95 | 0.94 |
|
| 29 |
+
| **Weighted Avg** | 0.93 | 0.93 | 0.93 |
|