Update README.md
Browse files
README.md
CHANGED
|
@@ -18,9 +18,9 @@ This model was merged using the [Linear DELLA](https://arxiv.org/abs/2406.11617)
|
|
| 18 |
### Models Merged
|
| 19 |
|
| 20 |
The following models were included in the merge:
|
| 21 |
-
* /
|
| 22 |
-
* /
|
| 23 |
-
* /
|
| 24 |
|
| 25 |
### Configuration
|
| 26 |
|
|
@@ -28,20 +28,20 @@ The following YAML configuration was used to produce this model:
|
|
| 28 |
|
| 29 |
```yaml
|
| 30 |
models:
|
| 31 |
-
- model:
|
| 32 |
parameters:
|
| 33 |
weight: 0.25
|
| 34 |
density: 0.4
|
| 35 |
-
- model:
|
| 36 |
parameters:
|
| 37 |
weight: 0.40
|
| 38 |
density: 0.6
|
| 39 |
-
- model:
|
| 40 |
parameters:
|
| 41 |
weight: 0.35
|
| 42 |
density: 0.5
|
| 43 |
merge_method: della_linear
|
| 44 |
-
base_model:
|
| 45 |
parameters:
|
| 46 |
epsilon: 0.05
|
| 47 |
lambda: 1
|
|
|
|
| 18 |
### Models Merged
|
| 19 |
|
| 20 |
The following models were included in the merge:
|
| 21 |
+
* /migtissera_Tess-3-Mistral-Large-2-123B
|
| 22 |
+
* /TheDrummer_Behemoth-123B-v1
|
| 23 |
+
* /gghfez_Writer-Large-2411-v2.1
|
| 24 |
|
| 25 |
### Configuration
|
| 26 |
|
|
|
|
| 28 |
|
| 29 |
```yaml
|
| 30 |
models:
|
| 31 |
+
- model: gghfez_Writer-Large-2411-v2.1
|
| 32 |
parameters:
|
| 33 |
weight: 0.25
|
| 34 |
density: 0.4
|
| 35 |
+
- model: TheDrummer_Behemoth-123B-v1
|
| 36 |
parameters:
|
| 37 |
weight: 0.40
|
| 38 |
density: 0.6
|
| 39 |
+
- model: migtissera_Tess-3-Mistral-Large-2-123B
|
| 40 |
parameters:
|
| 41 |
weight: 0.35
|
| 42 |
density: 0.5
|
| 43 |
merge_method: della_linear
|
| 44 |
+
base_model: gghfez_SmartMaid-123b
|
| 45 |
parameters:
|
| 46 |
epsilon: 0.05
|
| 47 |
lambda: 1
|