Hugging Face's logo

djuna
/
TEST-Q2.5-Lenned-14B

Text Generation
Transformers
Safetensors
qwen2
mergekit
Merge
conversational
text-generation-inference
Model card Files
xet
Community
3

Improve language tag

#3
by lbourdois - opened
base: refs/heads/main
←
from: refs/pr/3
Discussion Files changed
+97
-84
Files changed (1) hide show
  1. README.md +97 -84
README.md CHANGED
@@ -1,84 +1,97 @@
1
- ---
2
- base_model:
3
- - Qwen/Qwen2.5-14B
4
- - Krystalan/DRT-o1-14B
5
- - djuna/Q2.5-Veltha-14B-0.5
6
- - huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
7
- - netease-youdao/Confucius-o1-14B
8
- library_name: transformers
9
- tags:
10
- - mergekit
11
- - merge
12
-
13
- ---
14
- # merge
15
-
16
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
17
-
18
- ## Merge Details
19
- ### Merge Method
20
-
21
- This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.
22
-
23
- ### Models Merged
24
-
25
- The following models were included in the merge:
26
- * [Krystalan/DRT-o1-14B](https://huggingface.co/Krystalan/DRT-o1-14B)
27
- * [djuna/Q2.5-Veltha-14B-0.5](https://huggingface.co/djuna/Q2.5-Veltha-14B-0.5)
28
- * [huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated)
29
- * [netease-youdao/Confucius-o1-14B](https://huggingface.co/netease-youdao/Confucius-o1-14B)
30
-
31
- ### Configuration
32
-
33
- The following YAML configuration was used to produce this model:
34
-
35
- ```yaml
36
- models:
37
- - model: Qwen/Qwen2.5-14B
38
- - model: netease-youdao/Confucius-o1-14B
39
- - model: djuna/Q2.5-Veltha-14B-0.5
40
- - model: Krystalan/DRT-o1-14B
41
- - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
42
- merge_method: sce
43
- base_model: Qwen/Qwen2.5-14B
44
- tokenizer:
45
- source: "union"
46
- tokens:
47
- <|endoftext|>:
48
- source: "djuna/Q2.5-Veltha-14B-0.5"
49
- <|im_start|>:
50
- source: "djuna/Q2.5-Veltha-14B-0.5"
51
- <|im_end|>:
52
- source: "djuna/Q2.5-Veltha-14B-0.5"
53
- <|object_ref_start|>:
54
- source: "djuna/Q2.5-Veltha-14B-0.5"
55
- <|object_ref_end|>:
56
- source: "djuna/Q2.5-Veltha-14B-0.5"
57
- <|box_start|>:
58
- source: "djuna/Q2.5-Veltha-14B-0.5"
59
- <|box_end|>:
60
- source: "djuna/Q2.5-Veltha-14B-0.5"
61
- <｜end▁of▁sentence｜>:
62
- source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
63
- force: true
64
- <｜User｜>:
65
- source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
66
- force: true
67
- <｜Assistant｜>:
68
- source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
69
- force: true
70
- <｜begin▁of▁sentence｜>:
71
- source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
72
- force: true
73
- <|EOT|>:
74
- source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
75
- force: true
76
- <think>:
77
- source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
78
- force: true
79
- </think>:
80
- source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
81
- force: true
82
- dtype: float32
83
- out_dtype: bfloat16
84
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-14B
4
+ - Krystalan/DRT-o1-14B
5
+ - djuna/Q2.5-Veltha-14B-0.5
6
+ - huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
7
+ - netease-youdao/Confucius-o1-14B
8
+ library_name: transformers
9
+ tags:
10
+ - mergekit
11
+ - merge
12
+ language:
13
+ - zho
14
+ - eng
15
+ - fra
16
+ - spa
17
+ - por
18
+ - deu
19
+ - ita
20
+ - rus
21
+ - jpn
22
+ - kor
23
+ - vie
24
+ - tha
25
+ - ara
26
+ ---
27
+ # merge
28
+
29
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
30
+
31
+ ## Merge Details
32
+ ### Merge Method
33
+
34
+ This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.
35
+
36
+ ### Models Merged
37
+
38
+ The following models were included in the merge:
39
+ * [Krystalan/DRT-o1-14B](https://huggingface.co/Krystalan/DRT-o1-14B)
40
+ * [djuna/Q2.5-Veltha-14B-0.5](https://huggingface.co/djuna/Q2.5-Veltha-14B-0.5)
41
+ * [huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated)
42
+ * [netease-youdao/Confucius-o1-14B](https://huggingface.co/netease-youdao/Confucius-o1-14B)
43
+
44
+ ### Configuration
45
+
46
+ The following YAML configuration was used to produce this model:
47
+
48
+ ```yaml
49
+ models:
50
+ - model: Qwen/Qwen2.5-14B
51
+ - model: netease-youdao/Confucius-o1-14B
52
+ - model: djuna/Q2.5-Veltha-14B-0.5
53
+ - model: Krystalan/DRT-o1-14B
54
+ - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
55
+ merge_method: sce
56
+ base_model: Qwen/Qwen2.5-14B
57
+ tokenizer:
58
+ source: "union"
59
+ tokens:
60
+ <|endoftext|>:
61
+ source: "djuna/Q2.5-Veltha-14B-0.5"
62
+ <|im_start|>:
63
+ source: "djuna/Q2.5-Veltha-14B-0.5"
64
+ <|im_end|>:
65
+ source: "djuna/Q2.5-Veltha-14B-0.5"
66
+ <|object_ref_start|>:
67
+ source: "djuna/Q2.5-Veltha-14B-0.5"
68
+ <|object_ref_end|>:
69
+ source: "djuna/Q2.5-Veltha-14B-0.5"
70
+ <|box_start|>:
71
+ source: "djuna/Q2.5-Veltha-14B-0.5"
72
+ <|box_end|>:
73
+ source: "djuna/Q2.5-Veltha-14B-0.5"
74
+ <｜end▁of▁sentence｜>:
75
+ source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
76
+ force: true
77
+ <｜User｜>:
78
+ source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
79
+ force: true
80
+ <｜Assistant｜>:
81
+ source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
82
+ force: true
83
+ <｜begin▁of▁sentence｜>:
84
+ source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
85
+ force: true
86
+ <|EOT|>:
87
+ source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
88
+ force: true
89
+ <think>:
90
+ source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
91
+ force: true
92
+ </think>:
93
+ source: "huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated"
94
+ force: true
95
+ dtype: float32
96
+ out_dtype: bfloat16
97
+ ```