Files changed (1) hide show
  1. README.md +89 -76
README.md CHANGED
@@ -1,76 +1,89 @@
1
- ---
2
- base_model:
3
- - Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1
4
- - nvidia/AceMath-1.5B-Instruct
5
- - Qwen/Qwen2.5-1.5B-Instruct
6
- - bond005/meno-tiny-0.1
7
- - hotmailuser/QwenStock-1.7B
8
- - fblgit/miniclaus-qw1.5B-UNAMGS-GRPO
9
- - Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2
10
- - Sakalti/Saba1-1.8B
11
- - hotmailuser/QwenModelStock-1.8B
12
- - Sakalti/SJT-1.5B-Alpha
13
- - lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3
14
- - nvidia/AceInstruct-1.5B
15
- - Sakalti/Saba1.5-1.5B
16
- - fblgit/miniclaus-qw1.5B-UNAMGS
17
- library_name: transformers
18
- tags:
19
- - mergekit
20
- - merge
21
-
22
- ---
23
- # merge
24
-
25
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
26
-
27
- ## Merge Details
28
- ### Merge Method
29
-
30
- This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) as a base.
31
-
32
- ### Models Merged
33
-
34
- The following models were included in the merge:
35
- * [Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1](https://huggingface.co/Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1)
36
- * [nvidia/AceMath-1.5B-Instruct](https://huggingface.co/nvidia/AceMath-1.5B-Instruct)
37
- * [bond005/meno-tiny-0.1](https://huggingface.co/bond005/meno-tiny-0.1)
38
- * [hotmailuser/QwenStock-1.7B](https://huggingface.co/hotmailuser/QwenStock-1.7B)
39
- * [fblgit/miniclaus-qw1.5B-UNAMGS-GRPO](https://huggingface.co/fblgit/miniclaus-qw1.5B-UNAMGS-GRPO)
40
- * [Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2](https://huggingface.co/Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2)
41
- * [Sakalti/Saba1-1.8B](https://huggingface.co/Sakalti/Saba1-1.8B)
42
- * [hotmailuser/QwenModelStock-1.8B](https://huggingface.co/hotmailuser/QwenModelStock-1.8B)
43
- * [Sakalti/SJT-1.5B-Alpha](https://huggingface.co/Sakalti/SJT-1.5B-Alpha)
44
- * [lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3](https://huggingface.co/lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3)
45
- * [nvidia/AceInstruct-1.5B](https://huggingface.co/nvidia/AceInstruct-1.5B)
46
- * [Sakalti/Saba1.5-1.5B](https://huggingface.co/Sakalti/Saba1.5-1.5B)
47
- * [fblgit/miniclaus-qw1.5B-UNAMGS](https://huggingface.co/fblgit/miniclaus-qw1.5B-UNAMGS)
48
-
49
- ### Configuration
50
-
51
- The following YAML configuration was used to produce this model:
52
-
53
- ```yaml
54
- models:
55
- - model: bond005/meno-tiny-0.1
56
- - model: fblgit/miniclaus-qw1.5B-UNAMGS
57
- - model: fblgit/miniclaus-qw1.5B-UNAMGS-GRPO
58
- - model: hotmailuser/QwenModelStock-1.8B
59
- - model: hotmailuser/QwenStock-1.7B
60
- - model: lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3
61
- - model: nvidia/AceInstruct-1.5B
62
- - model: nvidia/AceMath-1.5B-Instruct
63
- - model: Qwen/Qwen2.5-1.5B-Instruct
64
- - model: Sakalti/Saba1.5-1.5B
65
- - model: Sakalti/Saba1-1.8B
66
- - model: Sakalti/SJT-1.5B-Alpha
67
- - model: Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1
68
- - model: Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2
69
- tokenizer:
70
- source: base
71
- merge_method: sce
72
- base_model: Qwen/Qwen2.5-1.5B-Instruct
73
- dtype: bfloat16
74
- parameters:
75
- int8_mask: true
76
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1
4
+ - nvidia/AceMath-1.5B-Instruct
5
+ - Qwen/Qwen2.5-1.5B-Instruct
6
+ - bond005/meno-tiny-0.1
7
+ - hotmailuser/QwenStock-1.7B
8
+ - fblgit/miniclaus-qw1.5B-UNAMGS-GRPO
9
+ - Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2
10
+ - Sakalti/Saba1-1.8B
11
+ - hotmailuser/QwenModelStock-1.8B
12
+ - Sakalti/SJT-1.5B-Alpha
13
+ - lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3
14
+ - nvidia/AceInstruct-1.5B
15
+ - Sakalti/Saba1.5-1.5B
16
+ - fblgit/miniclaus-qw1.5B-UNAMGS
17
+ library_name: transformers
18
+ tags:
19
+ - mergekit
20
+ - merge
21
+ language:
22
+ - zho
23
+ - eng
24
+ - fra
25
+ - spa
26
+ - por
27
+ - deu
28
+ - ita
29
+ - rus
30
+ - jpn
31
+ - kor
32
+ - vie
33
+ - tha
34
+ - ara
35
+ ---
36
+ # merge
37
+
38
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
39
+
40
+ ## Merge Details
41
+ ### Merge Method
42
+
43
+ This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) as a base.
44
+
45
+ ### Models Merged
46
+
47
+ The following models were included in the merge:
48
+ * [Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1](https://huggingface.co/Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1)
49
+ * [nvidia/AceMath-1.5B-Instruct](https://huggingface.co/nvidia/AceMath-1.5B-Instruct)
50
+ * [bond005/meno-tiny-0.1](https://huggingface.co/bond005/meno-tiny-0.1)
51
+ * [hotmailuser/QwenStock-1.7B](https://huggingface.co/hotmailuser/QwenStock-1.7B)
52
+ * [fblgit/miniclaus-qw1.5B-UNAMGS-GRPO](https://huggingface.co/fblgit/miniclaus-qw1.5B-UNAMGS-GRPO)
53
+ * [Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2](https://huggingface.co/Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2)
54
+ * [Sakalti/Saba1-1.8B](https://huggingface.co/Sakalti/Saba1-1.8B)
55
+ * [hotmailuser/QwenModelStock-1.8B](https://huggingface.co/hotmailuser/QwenModelStock-1.8B)
56
+ * [Sakalti/SJT-1.5B-Alpha](https://huggingface.co/Sakalti/SJT-1.5B-Alpha)
57
+ * [lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3](https://huggingface.co/lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3)
58
+ * [nvidia/AceInstruct-1.5B](https://huggingface.co/nvidia/AceInstruct-1.5B)
59
+ * [Sakalti/Saba1.5-1.5B](https://huggingface.co/Sakalti/Saba1.5-1.5B)
60
+ * [fblgit/miniclaus-qw1.5B-UNAMGS](https://huggingface.co/fblgit/miniclaus-qw1.5B-UNAMGS)
61
+
62
+ ### Configuration
63
+
64
+ The following YAML configuration was used to produce this model:
65
+
66
+ ```yaml
67
+ models:
68
+ - model: bond005/meno-tiny-0.1
69
+ - model: fblgit/miniclaus-qw1.5B-UNAMGS
70
+ - model: fblgit/miniclaus-qw1.5B-UNAMGS-GRPO
71
+ - model: hotmailuser/QwenModelStock-1.8B
72
+ - model: hotmailuser/QwenStock-1.7B
73
+ - model: lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3
74
+ - model: nvidia/AceInstruct-1.5B
75
+ - model: nvidia/AceMath-1.5B-Instruct
76
+ - model: Qwen/Qwen2.5-1.5B-Instruct
77
+ - model: Sakalti/Saba1.5-1.5B
78
+ - model: Sakalti/Saba1-1.8B
79
+ - model: Sakalti/SJT-1.5B-Alpha
80
+ - model: Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1
81
+ - model: Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2
82
+ tokenizer:
83
+ source: base
84
+ merge_method: sce
85
+ base_model: Qwen/Qwen2.5-1.5B-Instruct
86
+ dtype: bfloat16
87
+ parameters:
88
+ int8_mask: true
89
+ ```