Ateron commited on
Commit
2518ce7
·
verified ·
1 Parent(s): e58c8c7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -24
README.md CHANGED
@@ -14,32 +14,9 @@ This is a merge of pre-trained language models created using [mergekit](https://
14
  Same model, but different merge
15
  ### Merge Method
16
 
17
- This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using Magnum-Picaro-0.7-v2-12b as a base.
18
 
19
  ### Models Merged
20
 
21
  The following models were included in the merge:
22
  * Wayfarer-12B
23
-
24
- ### Configuration
25
-
26
- The following YAML configuration was used to produce this model:
27
-
28
- ```yaml
29
- models:
30
- - model: F:\AI\Pic\Magnum-Picaro-0.7-v2-12b
31
- parameters:
32
- density: [1, 0.7, 0.1] # density gradient
33
- weight: 1.0
34
- - model: F:\AI\Wayfarer\Wayfarer-12B
35
- parameters:
36
- density: 0.3
37
- weight: [0, 0.3, 0.7, 1] # weight gradient
38
- merge_method: ties
39
- base_model: F:\AI\Pic\Magnum-Picaro-0.7-v2-12b
40
- parameters:
41
- normalize: true
42
- int8_mask: true
43
- dtype: float16
44
-
45
- ```
 
14
  Same model, but different merge
15
  ### Merge Method
16
 
17
+ This model was merged using the [Linear] merge method using Magnum-Picaro-0.7-v2-12b as a base.
18
 
19
  ### Models Merged
20
 
21
  The following models were included in the merge:
22
  * Wayfarer-12B