nbeerbower commited on
Commit
fedc78f
1 Parent(s): 7e652ab

add readme

Browse files
Files changed (1) hide show
  1. README.md +39 -0
README.md CHANGED
@@ -1,3 +1,42 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ base_model:
4
+ - nbeerbower/bruphin-epsilon
5
+ - FelixChao/WestSeverus-7B-DPO-v2
6
+ - jondurbin/airoboros-m-7b-3.1.2
7
+ tags:
8
+ - mergekit
9
+ - moe
10
  ---
11
+
12
+ # SuperBruphin-3x7B
13
+
14
+ This is an experimental MoE model created using [mergekit](https://github.com/cg123/mergekit). (mixtral branch)
15
+
16
+
17
+ ### Models Merged
18
+
19
+ The following models were included in the merge:
20
+ * [nbeerbower/bruphin-epsilon](https://huggingface.co/nbeerbower/bruphin-epsilon)
21
+ * [FelixChao/WestSeverus-7B-DPO-v2](https://huggingface.co/FelixChao/WestSeverus-7B-DPO-v2)
22
+ * [jondurbin/airoboros-m-7b-3.1.2](https://huggingface.co/jondurbin/airoboros-m-7b-3.1.2)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ base_model: nbeerbower/bruphin-epsilon
30
+ gate_mode: hidden
31
+ dtype: bfloat16
32
+ experts:
33
+ - source_model: nbeerbower/bruphin-epsilon
34
+ positive_prompts:
35
+ - "Tell a story."
36
+ - source_model: FelixChao/WestSeverus-7B-DPO-v2
37
+ positive_prompts:
38
+ - "Solve this problem."
39
+ - source_model: jondurbin/airoboros-m-7b-3.1.2
40
+ positive_prompts:
41
+ - "Write a letter."
42
+ ```