Improve language tag

#1
by lbourdois - opened
Files changed (1) hide show
  1. README.md +82 -69
README.md CHANGED
@@ -1,69 +1,82 @@
1
- ---
2
- base_model:
3
- - gz987/qwen2.5-7b-cabs-v0.3
4
- - bunnycore/Qwen-2.5-7b-s1k-lora_model
5
- - simplescaling/s1.1-7B
6
- - gz987/qwen2.5-7b-cabs-v0.3
7
- - bunnycore/Qwen-2.5-7b-rp-lora
8
- - marcuscedricridia/pre-cursa-o1-v1.2
9
- - Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
10
- - Krystalan/DRT-7B
11
- - Qwen/Qwen2.5-7B-Instruct
12
- - open-r1/OlympicCoder-7B
13
- library_name: transformers
14
- tags:
15
- - mergekit
16
- - merge
17
-
18
- ---
19
- # merge
20
-
21
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
22
-
23
- ## Merge Details
24
- ### Merge Method
25
-
26
- This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) as a base.
27
-
28
- ### Models Merged
29
-
30
- The following models were included in the merge:
31
- * [gz987/qwen2.5-7b-cabs-v0.3](https://huggingface.co/gz987/qwen2.5-7b-cabs-v0.3) + [bunnycore/Qwen-2.5-7b-s1k-lora_model](https://huggingface.co/bunnycore/Qwen-2.5-7b-s1k-lora_model)
32
- * [simplescaling/s1.1-7B](https://huggingface.co/simplescaling/s1.1-7B)
33
- * [gz987/qwen2.5-7b-cabs-v0.3](https://huggingface.co/gz987/qwen2.5-7b-cabs-v0.3) + [bunnycore/Qwen-2.5-7b-rp-lora](https://huggingface.co/bunnycore/Qwen-2.5-7b-rp-lora)
34
- * [marcuscedricridia/pre-cursa-o1-v1.2](https://huggingface.co/marcuscedricridia/pre-cursa-o1-v1.2)
35
- * [Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview](https://huggingface.co/Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview)
36
- * [Krystalan/DRT-7B](https://huggingface.co/Krystalan/DRT-7B)
37
- * [open-r1/OlympicCoder-7B](https://huggingface.co/open-r1/OlympicCoder-7B)
38
-
39
- ### Configuration
40
-
41
- The following YAML configuration was used to produce this model:
42
-
43
- ```yaml
44
- models:
45
- - model: Krystalan/DRT-7B
46
- parameters:
47
- weight: 0.3
48
- - model: simplescaling/s1.1-7B
49
- parameters:
50
- weight: 0.3
51
- - model: Krystalan/DRT-7B
52
- parameters:
53
- weight: 0.3
54
- - model: open-r1/OlympicCoder-7B
55
- parameters:
56
- weight: 0.3
57
- - model: marcuscedricridia/pre-cursa-o1-v1.2
58
- parameters:
59
- weight: 0.3
60
- - model: Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
61
- - model: gz987/qwen2.5-7b-cabs-v0.3+bunnycore/Qwen-2.5-7b-s1k-lora_model
62
- - model: gz987/qwen2.5-7b-cabs-v0.3+bunnycore/Qwen-2.5-7b-rp-lora
63
- base_model: Qwen/Qwen2.5-7B-Instruct
64
- merge_method: model_stock
65
- parameters:
66
- dtype: bfloat16
67
- tokenizer_source: Qwen/Qwen2.5-7B-Instruct
68
-
69
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - gz987/qwen2.5-7b-cabs-v0.3
4
+ - bunnycore/Qwen-2.5-7b-s1k-lora_model
5
+ - simplescaling/s1.1-7B
6
+ - gz987/qwen2.5-7b-cabs-v0.3
7
+ - bunnycore/Qwen-2.5-7b-rp-lora
8
+ - marcuscedricridia/pre-cursa-o1-v1.2
9
+ - Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
10
+ - Krystalan/DRT-7B
11
+ - Qwen/Qwen2.5-7B-Instruct
12
+ - open-r1/OlympicCoder-7B
13
+ library_name: transformers
14
+ tags:
15
+ - mergekit
16
+ - merge
17
+ language:
18
+ - zho
19
+ - eng
20
+ - fra
21
+ - spa
22
+ - por
23
+ - deu
24
+ - ita
25
+ - rus
26
+ - jpn
27
+ - kor
28
+ - vie
29
+ - tha
30
+ - ara
31
+ ---
32
+ # merge
33
+
34
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
35
+
36
+ ## Merge Details
37
+ ### Merge Method
38
+
39
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) as a base.
40
+
41
+ ### Models Merged
42
+
43
+ The following models were included in the merge:
44
+ * [gz987/qwen2.5-7b-cabs-v0.3](https://huggingface.co/gz987/qwen2.5-7b-cabs-v0.3) + [bunnycore/Qwen-2.5-7b-s1k-lora_model](https://huggingface.co/bunnycore/Qwen-2.5-7b-s1k-lora_model)
45
+ * [simplescaling/s1.1-7B](https://huggingface.co/simplescaling/s1.1-7B)
46
+ * [gz987/qwen2.5-7b-cabs-v0.3](https://huggingface.co/gz987/qwen2.5-7b-cabs-v0.3) + [bunnycore/Qwen-2.5-7b-rp-lora](https://huggingface.co/bunnycore/Qwen-2.5-7b-rp-lora)
47
+ * [marcuscedricridia/pre-cursa-o1-v1.2](https://huggingface.co/marcuscedricridia/pre-cursa-o1-v1.2)
48
+ * [Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview](https://huggingface.co/Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview)
49
+ * [Krystalan/DRT-7B](https://huggingface.co/Krystalan/DRT-7B)
50
+ * [open-r1/OlympicCoder-7B](https://huggingface.co/open-r1/OlympicCoder-7B)
51
+
52
+ ### Configuration
53
+
54
+ The following YAML configuration was used to produce this model:
55
+
56
+ ```yaml
57
+ models:
58
+ - model: Krystalan/DRT-7B
59
+ parameters:
60
+ weight: 0.3
61
+ - model: simplescaling/s1.1-7B
62
+ parameters:
63
+ weight: 0.3
64
+ - model: Krystalan/DRT-7B
65
+ parameters:
66
+ weight: 0.3
67
+ - model: open-r1/OlympicCoder-7B
68
+ parameters:
69
+ weight: 0.3
70
+ - model: marcuscedricridia/pre-cursa-o1-v1.2
71
+ parameters:
72
+ weight: 0.3
73
+ - model: Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
74
+ - model: gz987/qwen2.5-7b-cabs-v0.3+bunnycore/Qwen-2.5-7b-s1k-lora_model
75
+ - model: gz987/qwen2.5-7b-cabs-v0.3+bunnycore/Qwen-2.5-7b-rp-lora
76
+ base_model: Qwen/Qwen2.5-7B-Instruct
77
+ merge_method: model_stock
78
+ parameters:
79
+ dtype: bfloat16
80
+ tokenizer_source: Qwen/Qwen2.5-7B-Instruct
81
+
82
+ ```