athirdpath commited on
Commit
a47fde4
1 Parent(s): f8d0908

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -0
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ ---
4
+ <p align="center"><img src="https://i.ibb.co/pbpJHpk/iambe-sml.png"/><font size="6"> <b>Iambe-20b-DARE-v2</b> </font></p>
5
+
6
+ ### Description
7
+
8
+ Named after a charming daughter of Echo and Pan in Greek myth, Iambe-20b-DARE-v2 is an improved [DARE](https://github.com/yule-BUAA/MergeLM) merge building on my recent experiments.
9
+
10
+ Iambe is intended to have the best realistically possible understanding of anatomy and of a scene's state for a 20b merge, while remaining personable and authentic in "voice".
11
+
12
+ ### Update Methodology
13
+
14
+ Noromaid and the general "no-robots" vibe didn't come through like I'd hoped in v1. My hypothesis is that the "soul" MythoMax and Noromaid have is probably distributed widely over many low-value deltas, due to the "ephemeral" nature of such a thing.
15
+
16
+ My old base model was likely giving DARE conniption fits, so I replaced that with a truly vanilla 20b base model.
17
+
18
+ Without a large base of dare_ties models to compare to, I'm basically feeling my way through this intuitively, so here's to good results!
19
+
20
+ ### Recipe
21
+ merge_method: dare_ties
22
+
23
+ - base_model: athirdpath/BigLlama-20b-v1.1
24
+
25
+ - model: Noromaid-20b-v0.1.1
26
+
27
+ weight: 0.38 / density: 0.60
28
+
29
+ - model: athirdpath/athirdpath/Eileithyia-20b
30
+
31
+ weight: 0.22 / density: 0.40
32
+
33
+ - model: athirdpath/CleverGirl-20b-Blended-v1.1-DARE
34
+
35
+ weight: 0.40 / density: 0.33
36
+
37
+ int8_mask: true
38
+
39
+ dtype: bfloat16