lbourdois commited on
Commit
1cb9316
·
verified ·
1 Parent(s): d6f43f8

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 +87 -75
README.md CHANGED
@@ -1,76 +1,88 @@
1
- ---
2
- base_model:
3
- - Qwen/Qwen2.5-14B
4
- - sometimesanotion/Qwenvergence-14B-v6-Prose-slerp
5
- library_name: transformers
6
- tags:
7
- - mergekit
8
- - merge
9
- license: apache-2.0
10
- language:
11
- - en
12
- metrics:
13
- - accuracy
14
- pipeline_tag: text-generation
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.
24
-
25
- ### Models Merged
26
-
27
- The following models were included in the merge:
28
- * [sometimesanotion/Qwenvergence-14B-v6-Prose-slerp](https://huggingface.co/sometimesanotion/Qwenvergence-14B-v6-Prose-slerp)
29
-
30
- ### Configuration
31
-
32
- The following YAML configuration was used to produce this model:
33
-
34
- ```yaml
35
- name: Qwenvergence-14B-v6-Prose-model_stock
36
- merge_method: model_stock
37
- base_model: Qwen/Qwen2.5-14B
38
- tokenizer_source: huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
39
- parameters:
40
- int8_mask: true
41
- normalize: true
42
- rescale: false
43
- models:
44
- - model: arcee-ai/Virtuoso-Small
45
- - model: sometimesanotion/Lamarck-14B-v0.3
46
- - model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
47
- - model: allura-org/TQ2.5-14B-Sugarquill-v1
48
- - model: oxyapi/oxy-1-small
49
- - model: v000000/Qwen2.5-Lumen-14B
50
- - model: sthenno-com/miscii-14b-1225
51
- - model: sthenno-com/miscii-14b-1225
52
- - model: underwoods/medius-erebus-magnum-14b
53
- - model: huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
54
- dtype: float32
55
- out_dtype: bfloat16
56
- ---
57
- # Nifty TIES, LoRA, SLERP involving the listed models
58
- ---
59
- name: Qwenvergence-14B-v6-Prose
60
- merge_method: ties
61
- base_model: Qwen/Qwen2.5-14B
62
- tokenizer_source: base
63
- parameters:
64
- density: 1.00
65
- weight: 1.00
66
- int8_mask: true
67
- normalize: true
68
- rescale: false
69
- dtype: float32
70
- out_dtype: bfloat16
71
- models:
72
- - model: sometimesanotion/Qwenvergence-14B-v6-Prose-slerp
73
- parameters:
74
- density: 1.00
75
- weight: 1.00
 
 
 
 
 
 
 
 
 
 
 
 
76
  ```
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-14B
4
+ - sometimesanotion/Qwenvergence-14B-v6-Prose-slerp
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+ license: apache-2.0
10
+ language:
11
+ - zho
12
+ - eng
13
+ - fra
14
+ - spa
15
+ - por
16
+ - deu
17
+ - ita
18
+ - rus
19
+ - jpn
20
+ - kor
21
+ - vie
22
+ - tha
23
+ - ara
24
+ metrics:
25
+ - accuracy
26
+ pipeline_tag: text-generation
27
+ ---
28
+ # merge
29
+
30
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
31
+
32
+ ## Merge Details
33
+ ### Merge Method
34
+
35
+ This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.
36
+
37
+ ### Models Merged
38
+
39
+ The following models were included in the merge:
40
+ * [sometimesanotion/Qwenvergence-14B-v6-Prose-slerp](https://huggingface.co/sometimesanotion/Qwenvergence-14B-v6-Prose-slerp)
41
+
42
+ ### Configuration
43
+
44
+ The following YAML configuration was used to produce this model:
45
+
46
+ ```yaml
47
+ name: Qwenvergence-14B-v6-Prose-model_stock
48
+ merge_method: model_stock
49
+ base_model: Qwen/Qwen2.5-14B
50
+ tokenizer_source: huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
51
+ parameters:
52
+ int8_mask: true
53
+ normalize: true
54
+ rescale: false
55
+ models:
56
+ - model: arcee-ai/Virtuoso-Small
57
+ - model: sometimesanotion/Lamarck-14B-v0.3
58
+ - model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
59
+ - model: allura-org/TQ2.5-14B-Sugarquill-v1
60
+ - model: oxyapi/oxy-1-small
61
+ - model: v000000/Qwen2.5-Lumen-14B
62
+ - model: sthenno-com/miscii-14b-1225
63
+ - model: sthenno-com/miscii-14b-1225
64
+ - model: underwoods/medius-erebus-magnum-14b
65
+ - model: huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
66
+ dtype: float32
67
+ out_dtype: bfloat16
68
+ ---
69
+ # Nifty TIES, LoRA, SLERP involving the listed models
70
+ ---
71
+ name: Qwenvergence-14B-v6-Prose
72
+ merge_method: ties
73
+ base_model: Qwen/Qwen2.5-14B
74
+ tokenizer_source: base
75
+ parameters:
76
+ density: 1.00
77
+ weight: 1.00
78
+ int8_mask: true
79
+ normalize: true
80
+ rescale: false
81
+ dtype: float32
82
+ out_dtype: bfloat16
83
+ models:
84
+ - model: sometimesanotion/Qwenvergence-14B-v6-Prose-slerp
85
+ parameters:
86
+ density: 1.00
87
+ weight: 1.00
88
  ```