Update README.md
Browse files
README.md
CHANGED
|
@@ -11,12 +11,21 @@ tags:
|
|
| 11 |
- transformers
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
# Introduction:
|
| 15 |
|
| 16 |
ElEmperador is an ORPO finetinue derived from the Mistral-7B-v0.1 base model.
|
| 17 |
|
| 18 |
The argilla/ultrafeedback-binarized-preferences-cleaned dataset was used to improve the performance of the model.
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
## Inference Script:
|
| 21 |
|
| 22 |
```yaml
|
|
|
|
| 11 |
- transformers
|
| 12 |
---
|
| 13 |
|
| 14 |
+
<h1 style="font-size: 2em;">✨ Introducing ElEmperador! ✨</h1>
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
# Introduction:
|
| 20 |
|
| 21 |
ElEmperador is an ORPO finetinue derived from the Mistral-7B-v0.1 base model.
|
| 22 |
|
| 23 |
The argilla/ultrafeedback-binarized-preferences-cleaned dataset was used to improve the performance of the model.
|
| 24 |
|
| 25 |
+
## Model Evals will be posted soon.
|
| 26 |
+
|
| 27 |
+
The model recipe: https://github.com/ParagEkbote/El-Emperador_ModelRecipe
|
| 28 |
+
|
| 29 |
## Inference Script:
|
| 30 |
|
| 31 |
```yaml
|