lucyknada commited on
Commit
b73d20f
·
verified ·
1 Parent(s): 3487944

Upload ./README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +55 -0
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - cgato/Nemo-12b-Humanize-SFT-v0.2-Quarter
4
+ - anthracite-org/magnum-v2-12b
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ ### exl2 quant (measurement.json in main branch)
12
+ ---
13
+ ### check revisions for quants
14
+ ---
15
+
16
+ # output
17
+
18
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
19
+
20
+ ## Merge Details
21
+ ### Merge Method
22
+
23
+ This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [cgato/Nemo-12b-Humanize-SFT-v0.2-Quarter](https://huggingface.co/cgato/Nemo-12b-Humanize-SFT-v0.2-Quarter) as a base.
24
+
25
+ ### Models Merged
26
+
27
+ The following models were included in the merge:
28
+ * [anthracite-org/magnum-v2-12b](https://huggingface.co/anthracite-org/magnum-v2-12b)
29
+
30
+ ### Configuration
31
+
32
+ The following YAML configuration was used to produce this model:
33
+
34
+ ```yaml
35
+ base_model: cgato/Nemo-12b-Humanize-SFT-v0.2-Quarter
36
+ config_source: anthracite-org/magnum-v2-12b
37
+ tokenizer_source: anthracite-org/magnum-v2-12b
38
+ dtype: float16
39
+ merge_method: dare_ties
40
+
41
+ parameters:
42
+ normalize: true
43
+ int8_mask: true
44
+
45
+ chat_template: "chatml"
46
+
47
+ models:
48
+ - model: anthracite-org/magnum-v2-12b
49
+ parameters:
50
+ weight: 0.4
51
+ - model: cgato/Nemo-12b-Humanize-SFT-v0.2-Quarter
52
+ parameters:
53
+ weight: 0.7
54
+
55
+ ```