Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,7 @@ tags:
|
|
| 7 |
- merge
|
| 8 |
|
| 9 |
---
|
| 10 |
-
# Llama-3-
|
| 11 |
The core idea came from @jukofyork, see this [issue;](https://github.com/arcee-ai/mergekit/issues/198)
|
| 12 |
|
| 13 |
As I understand, The concept of the idea is to make model think twice but leap same distances like original. but why 0.7071067812?
|
|
|
|
| 7 |
- merge
|
| 8 |
|
| 9 |
---
|
| 10 |
+
# Llama-3-13B-Instruct-attenuated
|
| 11 |
The core idea came from @jukofyork, see this [issue;](https://github.com/arcee-ai/mergekit/issues/198)
|
| 12 |
|
| 13 |
As I understand, The concept of the idea is to make model think twice but leap same distances like original. but why 0.7071067812?
|