MarinaraSpaghetti commited on
Commit
6a09377
1 Parent(s): 44fe13c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +47 -45
README.md CHANGED
@@ -1,45 +1,47 @@
1
- ---
2
- base_model: []
3
- library_name: transformers
4
- tags:
5
- - mergekit
6
- - merge
7
-
8
- ---
9
- # Nemomix-v3.0-12B
10
-
11
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
-
13
- ## Merge Details
14
- ### Merge Method
15
-
16
- This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using F:\mergekit\mistralaiMistral-Nemo-Base-2407 as a base.
17
-
18
- ### Models Merged
19
-
20
- The following models were included in the merge:
21
- * F:\mergekit\NeverSleepHistorical_lumi-nemo-e2.0
22
- * F:\mergekit\mistralaiMistral-Nemo-Instruct-2407
23
- * F:\mergekit\intervitens_mini-magnum-12b-v1.1
24
-
25
- ### Configuration
26
-
27
- The following YAML configuration was used to produce this model:
28
-
29
- ```yaml
30
- models:
31
- - model: F:\mergekit\NeverSleepHistorical_lumi-nemo-e2.0
32
- parameters:
33
- weight: 0.2
34
- - model: F:\mergekit\intervitens_mini-magnum-12b-v1.1
35
- parameters:
36
- weight: 0.4
37
- - model: F:\mergekit\mistralaiMistral-Nemo-Instruct-2407
38
- parameters:
39
- weight: 0.4
40
- merge_method: task_arithmetic
41
- base_model: F:\mergekit\mistralaiMistral-Nemo-Base-2407
42
- parameters:
43
- normalize: true
44
- dtype: bfloat16
45
- ```
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+ ---
8
+
9
+ # V4.0 is the best one, use that one.
10
+
11
+ # Nemomix-v3.0-12B
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using F:\mergekit\mistralaiMistral-Nemo-Base-2407 as a base.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * F:\mergekit\NeverSleepHistorical_lumi-nemo-e2.0
24
+ * F:\mergekit\mistralaiMistral-Nemo-Instruct-2407
25
+ * F:\mergekit\intervitens_mini-magnum-12b-v1.1
26
+
27
+ ### Configuration
28
+
29
+ The following YAML configuration was used to produce this model:
30
+
31
+ ```yaml
32
+ models:
33
+ - model: F:\mergekit\NeverSleepHistorical_lumi-nemo-e2.0
34
+ parameters:
35
+ weight: 0.2
36
+ - model: F:\mergekit\intervitens_mini-magnum-12b-v1.1
37
+ parameters:
38
+ weight: 0.4
39
+ - model: F:\mergekit\mistralaiMistral-Nemo-Instruct-2407
40
+ parameters:
41
+ weight: 0.4
42
+ merge_method: task_arithmetic
43
+ base_model: F:\mergekit\mistralaiMistral-Nemo-Base-2407
44
+ parameters:
45
+ normalize: true
46
+ dtype: bfloat16
47
+ ```