lbourdois commited on
Commit
4d3403a
·
verified ·
1 Parent(s): fc882d7

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 +59 -46
README.md CHANGED
@@ -1,46 +1,59 @@
1
- ---
2
- base_model:
3
- - trashpanda-org/Qwen2.5-32B-Marigold-v0
4
- - Qwen/Qwen2.5-32B
5
- library_name: transformers
6
- tags:
7
- - mergekit
8
- - merge
9
-
10
- ---
11
- # merge
12
-
13
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
-
15
- ## Merge Details
16
- ### Merge Method
17
-
18
- This model was merged using the [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using [trashpanda-org/Qwen2.5-32B-Marigold-v0](https://huggingface.co/trashpanda-org/Qwen2.5-32B-Marigold-v0) as a base.
19
-
20
- ### Models Merged
21
-
22
- The following models were included in the merge:
23
- * [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B)
24
-
25
- ### Configuration
26
-
27
- The following YAML configuration was used to produce this model:
28
-
29
- ```yaml
30
- # !!! For merging purposes
31
- models:
32
- # Finetune model
33
- - model: trashpanda-org/Qwen2.5-32B-Marigold-v0
34
- parameters:
35
- weight: 1.0
36
- # Base model
37
- - model: Qwen/Qwen2.5-32B
38
- parameters:
39
- weight: -1.0
40
- merge_method: task_arithmetic
41
- base_model: trashpanda-org/Qwen2.5-32B-Marigold-v0
42
- parameters:
43
- normalize: false
44
- dtype: float32
45
- out_dtype: bfloat16
46
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - trashpanda-org/Qwen2.5-32B-Marigold-v0
4
+ - Qwen/Qwen2.5-32B
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+ language:
10
+ - zho
11
+ - eng
12
+ - fra
13
+ - spa
14
+ - por
15
+ - deu
16
+ - ita
17
+ - rus
18
+ - jpn
19
+ - kor
20
+ - vie
21
+ - tha
22
+ - ara
23
+ ---
24
+ # merge
25
+
26
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
27
+
28
+ ## Merge Details
29
+ ### Merge Method
30
+
31
+ This model was merged using the [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using [trashpanda-org/Qwen2.5-32B-Marigold-v0](https://huggingface.co/trashpanda-org/Qwen2.5-32B-Marigold-v0) as a base.
32
+
33
+ ### Models Merged
34
+
35
+ The following models were included in the merge:
36
+ * [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B)
37
+
38
+ ### Configuration
39
+
40
+ The following YAML configuration was used to produce this model:
41
+
42
+ ```yaml
43
+ # !!! For merging purposes
44
+ models:
45
+ # Finetune model
46
+ - model: trashpanda-org/Qwen2.5-32B-Marigold-v0
47
+ parameters:
48
+ weight: 1.0
49
+ # Base model
50
+ - model: Qwen/Qwen2.5-32B
51
+ parameters:
52
+ weight: -1.0
53
+ merge_method: task_arithmetic
54
+ base_model: trashpanda-org/Qwen2.5-32B-Marigold-v0
55
+ parameters:
56
+ normalize: false
57
+ dtype: float32
58
+ out_dtype: bfloat16
59
+ ```