Update README.md
Browse files
README.md
CHANGED
|
@@ -23,7 +23,6 @@ tags:
|
|
| 23 |
|
| 24 |
ElEmperador is an ORPO-based finetune derived from the Mistral-7B-v0.1 base model.
|
| 25 |
|
| 26 |
-
The 'ultrafeedback-binarized-preferences-cleaned' dataset was used for training, albeit a small portion was used due to GPU constraints.
|
| 27 |
|
| 28 |
## Evals:
|
| 29 |
BLEU:0.209
|
|
@@ -62,5 +61,6 @@ if __name__ == "__main__":
|
|
| 62 |
|
| 63 |
## Results
|
| 64 |
|
| 65 |
-
ORPO is a viable RLHF algorithm to improve the performance of your models along with SFT finetuning.
|
| 66 |
leading to more user-friendly and acceptable results.
|
|
|
|
|
|
| 23 |
|
| 24 |
ElEmperador is an ORPO-based finetune derived from the Mistral-7B-v0.1 base model.
|
| 25 |
|
|
|
|
| 26 |
|
| 27 |
## Evals:
|
| 28 |
BLEU:0.209
|
|
|
|
| 61 |
|
| 62 |
## Results
|
| 63 |
|
| 64 |
+
Firstly,ORPO is a viable RLHF algorithm to improve the performance of your models along with SFT finetuning.Secondly, it also helps in aligning the model’s outputs more closely with human preferences,
|
| 65 |
leading to more user-friendly and acceptable results.
|
| 66 |
+
|