Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ Since R3: Tweaked ratios, Rosier's influence cut in half.
|
|
| 28 |
Since R4: Scrubbin' it down. +0.08 to Rosier (pre-normalization). Closing in on a good ratio.
|
| 29 |
|
| 30 |
Since R5: Doubled both ratios; since normalization is enabled, this *should* essentially be the same as R5, but it makes the numbers nicer to work with, as now they can be envisioned as a ratio against 1.
|
| 31 |
-
|
| 32 |
### Merge Method
|
| 33 |
|
| 34 |
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) as a base.
|
|
|
|
| 28 |
Since R4: Scrubbin' it down. +0.08 to Rosier (pre-normalization). Closing in on a good ratio.
|
| 29 |
|
| 30 |
Since R5: Doubled both ratios; since normalization is enabled, this *should* essentially be the same as R5, but it makes the numbers nicer to work with, as now they can be envisioned as a ratio against 1.
|
| 31 |
+
(Edit: They have the same SHA-256 sums, so they're literally identical.)
|
| 32 |
### Merge Method
|
| 33 |
|
| 34 |
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) as a base.
|