numb3r3 commited on
Commit
107ed28
·
verified ·
1 Parent(s): 0df23dc

init commit

Browse files
Files changed (1) hide show
  1. README.md +0 -78
README.md CHANGED
@@ -1,79 +1 @@
1
- ---
2
- base_model: []
3
- library_name: transformers
4
- tags:
5
- - mergekit
6
- - merge
7
 
8
- ---
9
- # 1226
10
-
11
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
-
13
- ## Merge Details
14
- ### Merge Method
15
-
16
- This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
17
-
18
- ### Models Merged
19
-
20
- The following models were included in the merge:
21
- * runs/qwen2.5-1.5b-step3-general
22
- * runs/qwen2.5-1.5b-step3-extend
23
- * runs/qwen2.5-1.5b-step3-json-v2
24
- * runs/qwen2.5-1.5b-step3-json-no-schema
25
- * runs/qwen2.5-1.5b-step3-verify
26
- * runs/qwen2.5-1.5b-step3-markdown-v2
27
- * runs/qwen2.5-1.5b-step3-qa-json
28
- * runs/qwen2.5-1.5b-step3-json
29
- * runs/qwen2.5-1.5b-step3-qa-markdown
30
- * runs/qwen2.5-1.5b-step3-contentaware-extract
31
- * runs/qwen2.5-1.5b-step3-markdown
32
- * runs/qwen2.5-1.5b-step3-refine
33
-
34
- ### Configuration
35
-
36
- The following YAML configuration was used to produce this model:
37
-
38
- ```yaml
39
- models:
40
- - model: runs/qwen2.5-1.5b-step3-markdown
41
- parameters:
42
- weight: 0.2
43
- - model: runs/qwen2.5-1.5b-step3-markdown-v2
44
- parameters:
45
- weight: 0.4
46
- - model: runs/qwen2.5-1.5b-step3-qa-markdown
47
- parameters:
48
- weight: 0.25
49
- - model: runs/qwen2.5-1.5b-step3-contentaware-extract
50
- parameters:
51
- weight: 0.25
52
- - model: runs/qwen2.5-1.5b-step3-json
53
- parameters:
54
- weight: 0.15
55
- - model: runs/qwen2.5-1.5b-step3-json-v2
56
- parameters:
57
- weight: 0.30
58
- - model: runs/qwen2.5-1.5b-step3-json-no-schema
59
- parameters:
60
- weight: 0.25
61
- - model: runs/qwen2.5-1.5b-step3-qa-json
62
- parameters:
63
- weight: 0.25
64
- - model: runs/qwen2.5-1.5b-step3-general
65
- parameters:
66
- weight: 0.15
67
- - model: runs/qwen2.5-1.5b-step3-verify
68
- parameters:
69
- weight: 0.25
70
- - model: runs/qwen2.5-1.5b-step3-refine
71
- parameters:
72
- weight: 0.25
73
- - model: runs/qwen2.5-1.5b-step3-extend
74
- parameters:
75
- weight: 0.35
76
- merge_method: linear
77
- dtype: bfloat16
78
-
79
- ```
 
 
 
 
 
 
 
1