Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,15 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
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".
|
| 5 |
+
|
| 6 |
+
The evaluation results are as follows:
|
| 7 |
+
|
| 8 |
+
| | Precision | Recall | F1-Score |
|
| 9 |
+
|----------------|:-----------:|:---------:|:----------:|
|
| 10 |
+
| **Non-Toxic** | 0.97 | 0.97 | 0.97 |
|
| 11 |
+
| **Toxic** | 0.89 | 0.89 | 0.89 |
|
| 12 |
+
| | | | |
|
| 13 |
+
| **Accuracy** | | | 0.95 |
|
| 14 |
+
| **Macro Avg** | 0.93 | 0.93 | 0.93 |
|
| 15 |
+
| **Weighted Avg** | 0.95 | 0.95 | 0.95 |
|