lbourdois commited on
Commit
01652cc
·
verified ·
1 Parent(s): b3c6f9b

Improve language tag

Browse files

Hi! As the model is multilingual, this is a PR to add other languages than English to the language tag to improve the referencing. Note that 29 languages are announced in the README, but only 13 are explicitly listed. I was therefore only able to add these 13 languages.

Files changed (1) hide show
  1. README.md +93 -80
README.md CHANGED
@@ -1,80 +1,93 @@
1
- ---
2
- base_model:
3
- - Cran-May/T.E-8.1
4
- - huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
5
- - EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
6
- - bunnycore/Qwen2.5-7B-HyperMix
7
- - c10x/CoT-2.5
8
- - Qwen/Qwen2.5-7B-Instruct
9
- - Qwen/Qwen2.5-7B
10
- library_name: transformers
11
- tags:
12
- - mergekit
13
- - merge
14
-
15
- ---
16
- # merge
17
-
18
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
19
-
20
- ## Merge Details
21
- ### Merge Method
22
-
23
- This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) as a base.
24
-
25
- ### Models Merged
26
-
27
- The following models were included in the merge:
28
- * [Cran-May/T.E-8.1](https://huggingface.co/Cran-May/T.E-8.1)
29
- * [huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2](https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2)
30
- * [EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1)
31
- * [bunnycore/Qwen2.5-7B-HyperMix](https://huggingface.co/bunnycore/Qwen2.5-7B-HyperMix)
32
- * [c10x/CoT-2.5](https://huggingface.co/c10x/CoT-2.5)
33
- * [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
34
-
35
- ### Configuration
36
-
37
- The following YAML configuration was used to produce this model:
38
-
39
- ```yaml
40
-
41
- models:
42
- - model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
43
- parameters:
44
- weight: 1
45
- density: 1
46
-
47
- - model: huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
48
- parameters:
49
- weight: 1
50
- density: 1
51
-
52
- - model: bunnycore/Qwen2.5-7B-HyperMix
53
- parameters:
54
- weight: 0.8
55
- density: 0.8
56
-
57
- - model: c10x/CoT-2.5
58
- parameters:
59
- weight: 0.5
60
- density: 0.5
61
-
62
- - model: Cran-May/T.E-8.1
63
- parameters:
64
- weight: 0.5
65
- density: 0.5
66
-
67
- - model: Qwen/Qwen2.5-7B-Instruct
68
- parameters:
69
- weight: 0.3
70
- density: 0.3
71
-
72
- merge_method: model_stock
73
- base_model: Qwen/Qwen2.5-7B
74
- parameters:
75
- density: 1
76
- normalize: true
77
- int8_mask: true
78
- dtype: bfloat16
79
-
80
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Cran-May/T.E-8.1
4
+ - huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
5
+ - EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
6
+ - bunnycore/Qwen2.5-7B-HyperMix
7
+ - c10x/CoT-2.5
8
+ - Qwen/Qwen2.5-7B-Instruct
9
+ - Qwen/Qwen2.5-7B
10
+ library_name: transformers
11
+ tags:
12
+ - mergekit
13
+ - merge
14
+ language:
15
+ - zho
16
+ - eng
17
+ - fra
18
+ - spa
19
+ - por
20
+ - deu
21
+ - ita
22
+ - rus
23
+ - jpn
24
+ - kor
25
+ - vie
26
+ - tha
27
+ - ara
28
+ ---
29
+ # merge
30
+
31
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
32
+
33
+ ## Merge Details
34
+ ### Merge Method
35
+
36
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) as a base.
37
+
38
+ ### Models Merged
39
+
40
+ The following models were included in the merge:
41
+ * [Cran-May/T.E-8.1](https://huggingface.co/Cran-May/T.E-8.1)
42
+ * [huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2](https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2)
43
+ * [EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1)
44
+ * [bunnycore/Qwen2.5-7B-HyperMix](https://huggingface.co/bunnycore/Qwen2.5-7B-HyperMix)
45
+ * [c10x/CoT-2.5](https://huggingface.co/c10x/CoT-2.5)
46
+ * [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
47
+
48
+ ### Configuration
49
+
50
+ The following YAML configuration was used to produce this model:
51
+
52
+ ```yaml
53
+
54
+ models:
55
+ - model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
56
+ parameters:
57
+ weight: 1
58
+ density: 1
59
+
60
+ - model: huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
61
+ parameters:
62
+ weight: 1
63
+ density: 1
64
+
65
+ - model: bunnycore/Qwen2.5-7B-HyperMix
66
+ parameters:
67
+ weight: 0.8
68
+ density: 0.8
69
+
70
+ - model: c10x/CoT-2.5
71
+ parameters:
72
+ weight: 0.5
73
+ density: 0.5
74
+
75
+ - model: Cran-May/T.E-8.1
76
+ parameters:
77
+ weight: 0.5
78
+ density: 0.5
79
+
80
+ - model: Qwen/Qwen2.5-7B-Instruct
81
+ parameters:
82
+ weight: 0.3
83
+ density: 0.3
84
+
85
+ merge_method: model_stock
86
+ base_model: Qwen/Qwen2.5-7B
87
+ parameters:
88
+ density: 1
89
+ normalize: true
90
+ int8_mask: true
91
+ dtype: bfloat16
92
+
93
+ ```