Commit ·
981b0ee
1
Parent(s): e584ad0
Update README.md
Browse files
README.md
CHANGED
|
@@ -44,6 +44,8 @@ The model was trained with a dataset composed of `prompt`, `completions`, and an
|
|
| 44 |
| 4 |0.024755|0.02109|
|
| 45 |
| 5 |0.019445|0.01416|
|
| 46 |
|
|
|
|
|
|
|
| 47 |
## Usage
|
| 48 |
|
| 49 |
Here's an example of how to use the `RewardModel` to score the quality of a response to a given prompt:
|
|
|
|
| 44 |
| 4 |0.024755|0.02109|
|
| 45 |
| 5 |0.019445|0.01416|
|
| 46 |
|
| 47 |
+
> Note: This repository has the notebook used to train this model.
|
| 48 |
+
|
| 49 |
## Usage
|
| 50 |
|
| 51 |
Here's an example of how to use the `RewardModel` to score the quality of a response to a given prompt:
|