Files changed (1) hide show
  1. README.md +62 -49
README.md CHANGED
@@ -1,49 +1,62 @@
1
- ---
2
- base_model:
3
- - Alfitaria/Q25-1.5B-VeoLu
4
- - Qwen/Qwen2.5-1.5B-Instruct
5
- - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
6
- library_name: transformers
7
- tags:
8
- - mergekit
9
- - merge
10
-
11
- ---
12
- # merge
13
-
14
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
15
-
16
- ## Merge Details
17
- ### Merge Method
18
-
19
- This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) as a base.
20
-
21
- ### Models Merged
22
-
23
- The following models were included in the merge:
24
- * [Alfitaria/Q25-1.5B-VeoLu](https://huggingface.co/Alfitaria/Q25-1.5B-VeoLu)
25
- * [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B)
26
-
27
- ### Configuration
28
-
29
- The following YAML configuration was used to produce this model:
30
-
31
- ```yaml
32
- models:
33
- - model: Qwen/Qwen2.5-1.5B-Instruct
34
- # No parameters necessary for base model
35
- - model: Alfitaria/Q25-1.5B-VeoLu
36
- parameters:
37
- density: 0.56
38
- weight: 0.6
39
- - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
40
- parameters:
41
- density: 0.44
42
- weight: 0.4
43
- merge_method: dare_ties
44
- base_model: Qwen/Qwen2.5-1.5B-Instruct
45
- parameters:
46
- int8_mask: true
47
- dtype: float16
48
-
49
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Alfitaria/Q25-1.5B-VeoLu
4
+ - Qwen/Qwen2.5-1.5B-Instruct
5
+ - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
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
+ # merge
26
+
27
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
28
+
29
+ ## Merge Details
30
+ ### Merge Method
31
+
32
+ This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) as a base.
33
+
34
+ ### Models Merged
35
+
36
+ The following models were included in the merge:
37
+ * [Alfitaria/Q25-1.5B-VeoLu](https://huggingface.co/Alfitaria/Q25-1.5B-VeoLu)
38
+ * [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B)
39
+
40
+ ### Configuration
41
+
42
+ The following YAML configuration was used to produce this model:
43
+
44
+ ```yaml
45
+ models:
46
+ - model: Qwen/Qwen2.5-1.5B-Instruct
47
+ # No parameters necessary for base model
48
+ - model: Alfitaria/Q25-1.5B-VeoLu
49
+ parameters:
50
+ density: 0.56
51
+ weight: 0.6
52
+ - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
53
+ parameters:
54
+ density: 0.44
55
+ weight: 0.4
56
+ merge_method: dare_ties
57
+ base_model: Qwen/Qwen2.5-1.5B-Instruct
58
+ parameters:
59
+ int8_mask: true
60
+ dtype: float16
61
+
62
+ ```