File size: 3,237 Bytes
11addf9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-v0.1
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Mistral-7B-v0.1-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: stabilityai/japanese-stablelm-base-gamma-7b
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: DataPilot/ArrowPro-7B-KillerWhale
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: ArrowPro-7B-KillerWhale-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: nitky/RP-7b-instruct
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: RP-7b-instruct-VE-Swallow-MS
---
merge_method: task_arithmetic
base_model: mistralai/Mistral-7B-Instruct-v0.3
models:
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight:
      - filter: embed_tokens
        value: 1.0
      - value: 0
dtype: bfloat16
tokenizer_source: model:tokyotech-llm/Swallow-MS-7b-v0.1
name: Mistral-7B-Instruct-v0.3-VE-Swallow-MS
---
merge_method: linear
models:
  - model: nitky/Oumuamua-7b-base
    parameters:
      weight: 1.0
  - model: tokyotech-llm/Swallow-MS-7b-instruct-v0.1
    parameters:
      weight: 0.8
  - model: tokyotech-llm/Swallow-MS-7b-v0.1
    parameters:
      weight: -0.8
  - model: Mistral-7B-Instruct-v0.3-VE-Swallow-MS
    parameters:
      weight: 0.8
  - model: Mistral-7B-v0.1-VE-Swallow-MS
    parameters:
      weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-alpha
---
merge_method: linear
models:
  - model: nitky/Oumuamua-7b-base
    parameters:
      weight: 1.0
  - model: ArrowPro-7B-KillerWhale-VE-Swallow-MS # include Mistral-7B-Instruct-v0.3
    parameters:
      weight: 0.8
  - model: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
    parameters:
      weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-beta
---
merge_method: linear
models:
  - model: nitky/Oumuamua-7b-base
    parameters:
      weight: 1.0
  - model: RP-7b-instruct-VE-Swallow-MS
    parameters:
      weight: 0.8
  - model: japanese-stablelm-base-gamma-7b-VE-Swallow-MS
    parameters:
      weight: -0.8
  - model: Mistral-7B-Instruct-v0.3-VE-Swallow-MS
    parameters:
      weight: 0.8
  - model: Mistral-7B-v0.1-VE-Swallow-MS
    parameters:
      weight: -0.8
dtype: bfloat16
name: Oumuamua-7b-instruct-gamma
---
merge_method: model_stock
base_model: nitky/Oumuamua-7b-base
models:
  - model: Oumuamua-7b-instruct-alpha
  - model: Oumuamua-7b-instruct-beta
  - model: Oumuamua-7b-instruct-gamma
dtype: bfloat16
name: Oumuamua-7b-instruct