Update README.md
Browse files
README.md
CHANGED
|
@@ -36,7 +36,8 @@ lora_target_modules:
|
|
| 36 |
```
|
| 37 |
|
| 38 |
The model is coherent even with training the "zeroed" loayers and can write well. In the next experiment, all layers will be finetuned as this was
|
| 39 |
-
the recommendation from [Charles Goddard] - thank you for the method of merging
|
|
|
|
| 40 |
|
| 41 |
```yaml
|
| 42 |
The following hyperparameters were used during training:
|
|
|
|
| 36 |
```
|
| 37 |
|
| 38 |
The model is coherent even with training the "zeroed" loayers and can write well. In the next experiment, all layers will be finetuned as this was
|
| 39 |
+
the recommendation from [Charles Goddard](https://huggingface.co/chargoddard) - thank you for sharing the method of merging as well as Toasty
|
| 40 |
+
Pigeon for bringing it to my attention!
|
| 41 |
|
| 42 |
```yaml
|
| 43 |
The following hyperparameters were used during training:
|