Update README.md
Browse files
README.md
CHANGED
|
@@ -6,3 +6,12 @@ tags: []
|
|
| 6 |
# Model Card for Model ID
|
| 7 |
|
| 8 |
Gemma-2-9b model, finetuned with ORPO trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
# Model Card for Model ID
|
| 7 |
|
| 8 |
Gemma-2-9b model, finetuned with ORPO trainer
|
| 9 |
+
|
| 10 |
+
## Training Procedure
|
| 11 |
+
|
| 12 |
+
Trained with ORPOTrainer with rsLoRA.
|
| 13 |
+
|
| 14 |
+
## Dataset
|
| 15 |
+
|
| 16 |
+
Trained on [mlabonne/orpo-dpo-mix-40k](https://huggingface.co/datasets/mlabonne/orpo-dpo-mix-40k) dataset.
|
| 17 |
+
|