Files changed (1) hide show
  1. README.md +70 -58
README.md CHANGED
@@ -1,59 +1,71 @@
1
- ---
2
- base_model:
3
- - Qwen/Qwen2.5-32B-Instruct
4
- - Qwen/QwQ-32B
5
- - allura-org/Qwen2.5-32b-RP-Ink
6
- - fblgit/TheBeagle-v2beta-32B-MGS
7
- - Qwen/Qwen2.5-Coder-32B
8
- - Qwen/Qwen2.5-32B
9
- - huihui-ai/QwQ-32B-Preview-abliterated
10
- - tanliboy/lambda-qwen2.5-32b-dpo-test
11
- library_name: transformers
12
- tags:
13
- - mergekit
14
- - merge
15
- license: mit
16
- language:
17
- - en
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/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) as a base.
27
-
28
- ### Models Merged
29
-
30
- The following models were included in the merge:
31
- * [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B)
32
- * [allura-org/Qwen2.5-32b-RP-Ink](https://huggingface.co/allura-org/Qwen2.5-32b-RP-Ink)
33
- * [fblgit/TheBeagle-v2beta-32B-MGS](https://huggingface.co/fblgit/TheBeagle-v2beta-32B-MGS)
34
- * [Qwen/Qwen2.5-Coder-32B](https://huggingface.co/Qwen/Qwen2.5-Coder-32B)
35
- * [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B)
36
- * [huihui-ai/QwQ-32B-Preview-abliterated](https://huggingface.co/huihui-ai/QwQ-32B-Preview-abliterated)
37
- * [tanliboy/lambda-qwen2.5-32b-dpo-test](https://huggingface.co/tanliboy/lambda-qwen2.5-32b-dpo-test)
38
-
39
- ### Configuration
40
-
41
- The following YAML configuration was used to produce this model:
42
-
43
- ```yaml
44
- models:
45
- - model: Qwen/QwQ-32B
46
- - model: huihui-ai/QwQ-32B-Preview-abliterated #uncensored
47
- - model: Qwen/Qwen2.5-32B #text generation
48
- - model: Qwen/Qwen2.5-32B-Instruct #chat assistant
49
- - model: Qwen/Qwen2.5-Coder-32B #coding
50
- - model: fblgit/TheBeagle-v2beta-32B-MGS #math
51
- - model: tanliboy/lambda-qwen2.5-32b-dpo-test #dpo
52
- - model: allura-org/Qwen2.5-32b-RP-Ink # RP
53
- merge_method: model_stock
54
- base_model: Qwen/Qwen2.5-32B-Instruct
55
- normalize: true
56
- int8_mask: true
57
- dtype: bfloat16
58
-
 
 
 
 
 
 
 
 
 
 
 
 
59
  ```
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-32B-Instruct
4
+ - Qwen/QwQ-32B
5
+ - allura-org/Qwen2.5-32b-RP-Ink
6
+ - fblgit/TheBeagle-v2beta-32B-MGS
7
+ - Qwen/Qwen2.5-Coder-32B
8
+ - Qwen/Qwen2.5-32B
9
+ - huihui-ai/QwQ-32B-Preview-abliterated
10
+ - tanliboy/lambda-qwen2.5-32b-dpo-test
11
+ library_name: transformers
12
+ tags:
13
+ - mergekit
14
+ - merge
15
+ license: mit
16
+ language:
17
+ - zho
18
+ - eng
19
+ - fra
20
+ - spa
21
+ - por
22
+ - deu
23
+ - ita
24
+ - rus
25
+ - jpn
26
+ - kor
27
+ - vie
28
+ - tha
29
+ - ara
30
+ ---
31
+ # merge
32
+
33
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
34
+
35
+ ## Merge Details
36
+ ### Merge Method
37
+
38
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) as a base.
39
+
40
+ ### Models Merged
41
+
42
+ The following models were included in the merge:
43
+ * [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B)
44
+ * [allura-org/Qwen2.5-32b-RP-Ink](https://huggingface.co/allura-org/Qwen2.5-32b-RP-Ink)
45
+ * [fblgit/TheBeagle-v2beta-32B-MGS](https://huggingface.co/fblgit/TheBeagle-v2beta-32B-MGS)
46
+ * [Qwen/Qwen2.5-Coder-32B](https://huggingface.co/Qwen/Qwen2.5-Coder-32B)
47
+ * [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B)
48
+ * [huihui-ai/QwQ-32B-Preview-abliterated](https://huggingface.co/huihui-ai/QwQ-32B-Preview-abliterated)
49
+ * [tanliboy/lambda-qwen2.5-32b-dpo-test](https://huggingface.co/tanliboy/lambda-qwen2.5-32b-dpo-test)
50
+
51
+ ### Configuration
52
+
53
+ The following YAML configuration was used to produce this model:
54
+
55
+ ```yaml
56
+ models:
57
+ - model: Qwen/QwQ-32B
58
+ - model: huihui-ai/QwQ-32B-Preview-abliterated #uncensored
59
+ - model: Qwen/Qwen2.5-32B #text generation
60
+ - model: Qwen/Qwen2.5-32B-Instruct #chat assistant
61
+ - model: Qwen/Qwen2.5-Coder-32B #coding
62
+ - model: fblgit/TheBeagle-v2beta-32B-MGS #math
63
+ - model: tanliboy/lambda-qwen2.5-32b-dpo-test #dpo
64
+ - model: allura-org/Qwen2.5-32b-RP-Ink # RP
65
+ merge_method: model_stock
66
+ base_model: Qwen/Qwen2.5-32B-Instruct
67
+ normalize: true
68
+ int8_mask: true
69
+ dtype: bfloat16
70
+
71
  ```