DataSoul lbourdois commited on
Commit
2bb7402
·
verified ·
1 Parent(s): a5ef912

Improve language tag (#2)

Browse files

- Improve language tag (1b4f9b940339ee7fc50c57e095b9daa786b4d168)


Co-authored-by: Loïck BOURDOIS <[email protected]>

Files changed (1) hide show
  1. README.md +66 -53
README.md CHANGED
@@ -1,53 +1,66 @@
1
- ---
2
- base_model:
3
- - zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
4
- - Qwen/QwQ-32B
5
- - Qwen/Qwen2.5-32B-Instruct
6
- library_name: transformers
7
- tags:
8
- - mergekit
9
- - merge
10
-
11
- ---
12
- More recommended [DataSoul/QAQ-32B-merge3](https://huggingface.co/DataSoul/QAQ-32B-merge3)
13
- But it is still not a 'thinking' model.
14
-
15
- # merge
16
-
17
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
18
-
19
- ## Merge Details
20
- ### Merge Method
21
-
22
- This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) as a base.
23
-
24
- ### Models Merged
25
-
26
- The following models were included in the merge:
27
- * [zetasepic/Qwen2.5-32B-Instruct-abliterated-v2](https://huggingface.co/zetasepic/Qwen2.5-32B-Instruct-abliterated-v2)
28
- * [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)
29
-
30
- ### Configuration
31
-
32
- The following YAML configuration was used to produce this model:
33
-
34
- ```yaml
35
- models:
36
- - model: Qwen/QwQ-32B
37
- #no parameters necessary for base model
38
- - model: zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
39
- parameters:
40
- weight: 1
41
- density: 1
42
- - model: Qwen/Qwen2.5-32B-Instruct
43
- parameters:
44
- weight: -1
45
- density: 1
46
- merge_method: ties
47
- base_model: Qwen/QwQ-32B
48
- parameters:
49
- normalize: true
50
- int8_mask: true
51
- dtype: float16
52
-
53
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
4
+ - Qwen/QwQ-32B
5
+ - Qwen/Qwen2.5-32B-Instruct
6
+ library_name: transformers
7
+ tags:
8
+ - mergekit
9
+ - merge
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
+ ---
25
+ More recommended [DataSoul/QAQ-32B-merge3](https://huggingface.co/DataSoul/QAQ-32B-merge3)
26
+ But it is still not a 'thinking' model.
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/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) as a base.
36
+
37
+ ### Models Merged
38
+
39
+ The following models were included in the merge:
40
+ * [zetasepic/Qwen2.5-32B-Instruct-abliterated-v2](https://huggingface.co/zetasepic/Qwen2.5-32B-Instruct-abliterated-v2)
41
+ * [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)
42
+
43
+ ### Configuration
44
+
45
+ The following YAML configuration was used to produce this model:
46
+
47
+ ```yaml
48
+ models:
49
+ - model: Qwen/QwQ-32B
50
+ #no parameters necessary for base model
51
+ - model: zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
52
+ parameters:
53
+ weight: 1
54
+ density: 1
55
+ - model: Qwen/Qwen2.5-32B-Instruct
56
+ parameters:
57
+ weight: -1
58
+ density: 1
59
+ merge_method: ties
60
+ base_model: Qwen/QwQ-32B
61
+ parameters:
62
+ normalize: true
63
+ int8_mask: true
64
+ dtype: float16
65
+
66
+ ```