cookinai commited on
Commit
f367993
1 Parent(s): b21daf4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -0
README.md CHANGED
@@ -1,3 +1,27 @@
1
  ---
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
  ---
4
+ Heard alot in the commuity about jondurbin/bagel-dpo-7b-v0.1 and it sounds intresting.
5
+
6
+ Slerp Merge of AIDC-ai-business/Marcoroni-7B-v3 and jondurbin/bagel-dpo-7b-v0.1
7
+
8
+ .yaml file for mergekit
9
+
10
+ ```.yaml:
11
+ slices:
12
+ - sources:
13
+ - model: AIDC-ai-business/Marcoroni-7B-v3
14
+ layer_range: [0, 32]
15
+ - model: jondurbin/bagel-dpo-7b-v0.1
16
+ layer_range: [0, 32]
17
+ merge_method: slerp
18
+ base_model: AIDC-ai-business/Marcoroni-7B-v3
19
+ parameters:
20
+ t:
21
+ - filter: self_attn
22
+ value: [0, 0.5, 0.3, 0.7, 1]
23
+ - filter: mlp
24
+ value: [1, 0.5, 0.7, 0.3, 0]
25
+ - value: 0.5 # fallback for rest of tensors
26
+ dtype: bfloat16
27
+ ```