Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ pipeline_tag: text-generation
|
|
| 19 |
|
| 20 |
### Apply Delta Weights
|
| 21 |
|
| 22 |
-
Stable Beluga 1 cannot be used from the `stabilityai/StableBeluga1-Delta` weights alone. To obtain the correct model, one must add back the difference between LLaMA 65B and `stabilityai/
|
| 23 |
|
| 24 |
|
| 25 |
```sh
|
|
@@ -74,7 +74,7 @@ The output of Stable Beluga 1
|
|
| 74 |
|
| 75 |
### Training Dataset
|
| 76 |
|
| 77 |
-
`
|
| 78 |
|
| 79 |
### Training Procedure
|
| 80 |
|
|
|
|
| 19 |
|
| 20 |
### Apply Delta Weights
|
| 21 |
|
| 22 |
+
Stable Beluga 1 cannot be used from the `stabilityai/StableBeluga1-Delta` weights alone. To obtain the correct model, one must add back the difference between LLaMA 65B and `stabilityai/StableBeluga1-Delta` weights. We provide the [`apply_delta.py`](https://huggingface.co/stabilityai/StabelBeluga1-Delta/raw/main/apply_delta.py) script to automate the conversion, which you can run as:
|
| 23 |
|
| 24 |
|
| 25 |
```sh
|
|
|
|
| 74 |
|
| 75 |
### Training Dataset
|
| 76 |
|
| 77 |
+
`Stable Beluga 1` is trained on our internal Orca-style dataset
|
| 78 |
|
| 79 |
### Training Procedure
|
| 80 |
|