Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,10 @@ The models in this merge were chosen for their attention to detail and/or their
|
|
| 16 |
|
| 17 |
Based on each model's individual strength, weights were applied to prioritize the model's intelligence (self-attention weights) or style/creativity (multi-layer perceptron weights).
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
## Merge Details
|
| 20 |
### Merge Method
|
| 21 |
|
|
|
|
| 16 |
|
| 17 |
Based on each model's individual strength, weights were applied to prioritize the model's intelligence (self-attention weights) or style/creativity (multi-layer perceptron weights).
|
| 18 |
|
| 19 |
+
# Usage
|
| 20 |
+
|
| 21 |
+
Recommended prompt format is Alpaca, as this is most widely accepted by the component models.
|
| 22 |
+
|
| 23 |
## Merge Details
|
| 24 |
### Merge Method
|
| 25 |
|