Update README.md
Browse files
README.md
CHANGED
|
@@ -54,4 +54,6 @@ parameters:
|
|
| 54 |
t:
|
| 55 |
- value: [0, 0, 0.3, 0.4, 0.5, 0.6, 0.5, 0.4, 0.3, 0, 0]
|
| 56 |
dtype: bfloat16
|
| 57 |
-
```
|
|
|
|
|
|
|
|
|
| 54 |
t:
|
| 55 |
- value: [0, 0, 0.3, 0.4, 0.5, 0.6, 0.5, 0.4, 0.3, 0, 0]
|
| 56 |
dtype: bfloat16
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
*The idea here is that Gutenberg DPO stays in the output/input 100% while merging smoothly with the base instruct model in the deeper layers to heal loss and increase intelligence.*
|