Improve language tag

#1
by lbourdois - opened
Files changed (1) hide show
  1. README.md +71 -57
README.md CHANGED
@@ -1,57 +1,71 @@
1
- ---
2
- base_model:
3
- - Qwen/Qwen2.5-0.5B-Instruct
4
- library_name: transformers
5
- tags:
6
- - mergekit
7
- - merge
8
- inference: true
9
- pipeline_tag: text-generation
10
- widget:
11
- - messages:
12
- - role: user
13
- content: こんにちは!
14
- - messages:
15
- - role: user
16
- content: 魚を捌くのは難しいですか?
17
- - messages:
18
- - role: user
19
- content: ナイジェリアの首都はどこですか?
20
- - messages:
21
- - role: user
22
- content: hello!
23
- license: apache-2.0
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 passthrough merge method.
33
-
34
- ### Models Merged
35
-
36
- The following models were included in the merge:
37
- * [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
38
-
39
- ### Configuration
40
-
41
- The following YAML configuration was used to produce this model:
42
-
43
- ```yaml
44
- slices:
45
- - sources:
46
- - layer_range: [0, 12]
47
- model: Qwen/Qwen2.5-0.5B-Instruct
48
- - sources:
49
- - layer_range: [12, 24]
50
- model: Qwen/Qwen2.5-0.5B-Instruct
51
- - sources:
52
- - layer_range: [0, 24]
53
- model: Qwen/Qwen2.5-0.5B-Instruct
54
- merge_method: passthrough
55
- dtype: bfloat16
56
-
57
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-0.5B-Instruct
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+ inference: true
9
+ pipeline_tag: text-generation
10
+ widget:
11
+ - messages:
12
+ - role: user
13
+ content: こんにちは!
14
+ - messages:
15
+ - role: user
16
+ content: 魚を捌くのは難しいですか?
17
+ - messages:
18
+ - role: user
19
+ content: ナイジェリアの首都はどこですか?
20
+ - messages:
21
+ - role: user
22
+ content: hello!
23
+ license: apache-2.0
24
+ language:
25
+ - zho
26
+ - eng
27
+ - fra
28
+ - spa
29
+ - por
30
+ - deu
31
+ - ita
32
+ - rus
33
+ - jpn
34
+ - kor
35
+ - vie
36
+ - tha
37
+ - ara
38
+ ---
39
+ # merge
40
+
41
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
42
+
43
+ ## Merge Details
44
+ ### Merge Method
45
+
46
+ This model was merged using the passthrough merge method.
47
+
48
+ ### Models Merged
49
+
50
+ The following models were included in the merge:
51
+ * [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
52
+
53
+ ### Configuration
54
+
55
+ The following YAML configuration was used to produce this model:
56
+
57
+ ```yaml
58
+ slices:
59
+ - sources:
60
+ - layer_range: [0, 12]
61
+ model: Qwen/Qwen2.5-0.5B-Instruct
62
+ - sources:
63
+ - layer_range: [12, 24]
64
+ model: Qwen/Qwen2.5-0.5B-Instruct
65
+ - sources:
66
+ - layer_range: [0, 24]
67
+ model: Qwen/Qwen2.5-0.5B-Instruct
68
+ merge_method: passthrough
69
+ dtype: bfloat16
70
+
71
+ ```