Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,9 @@ tags:
|
|
| 10 |
---
|
| 11 |
# merge
|
| 12 |
|
| 13 |
-
The merits of multi-stage arcee_fusion merges are clearly shown in [sometimesanotion/Lamarck-14B-v0.7-Fusion](https://huggingface.co/sometimesanotion/Lamarck-14B-v0.7-Fusion), which has a valuable uptick in GPQA over its predecessors. Will its gains be maintained with a modified version of the SLERP recipe from [suayptalha/Lamarckvergence-14B](https://huggingface.co/suayptalha/Lamarckvergence-14B)?
|
|
|
|
|
|
|
| 14 |
|
| 15 |
## Merge Details
|
| 16 |
### Merge Method
|
|
|
|
| 10 |
---
|
| 11 |
# merge
|
| 12 |
|
| 13 |
+
The merits of multi-stage arcee_fusion merges are clearly shown in [sometimesanotion/Lamarck-14B-v0.7-Fusion](https://huggingface.co/sometimesanotion/Lamarck-14B-v0.7-Fusion), which has a valuable uptick in GPQA over its predecessors. Will its gains be maintained with a modified version of the SLERP recipe from [suayptalha/Lamarckvergence-14B](https://huggingface.co/suayptalha/Lamarckvergence-14B)? Let's find out what these weights for self-attention and perceptrons can unlock in this merge.
|
| 14 |
+
|
| 15 |
+
Why isn't this the next version of Lamarck? It has not undergone the highly layer-targeting merges that go into a Lamarck release, and to truly refine Lamarck v0.7 requires top-notch components. This one, perhaps.
|
| 16 |
|
| 17 |
## Merge Details
|
| 18 |
### Merge Method
|