Nexesenex commited on
Commit
3599b89
·
verified ·
1 Parent(s): df797df

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -35,12 +35,12 @@ Also a big-up to SteelSkull, observing him cooking Nevoria decided me to try to
35
  ---
36
  # historic
37
 
38
- 1) On the Kostume series started on the 11/02/0205 I tried to make a triple stock merge of 3 intermediary stock merges of a dozen of model or so.
39
  This, to see if I could pile up their abilities.
40
 
41
- Not bad, but nothing special about it, it's a bit hard for me to judge at 3b.
42
 
43
- 2) On the Kermes series started the day after, I defined a simpler approach:
44
 
45
  - Perplexity is the main constraint. Usual L3.2 3b finetunes are around 10.5-11 ppl512wikieng, Hermes is around 9.5.
46
  - I also measure in French and Serbian to observe the variances.
 
35
  ---
36
  # historic
37
 
38
+ First : On the Kostume series started on the 11/02/0205 I tried to make a triple stock merge of 3 intermediary stock merges of a dozen of model or so.
39
  This, to see if I could pile up their abilities.
40
 
41
+ - Not bad, but nothing special about it, it's a bit hard for me to judge at 3b.
42
 
43
+ Second : On the Kermes series started the day after, I defined a simpler approach:
44
 
45
  - Perplexity is the main constraint. Usual L3.2 3b finetunes are around 10.5-11 ppl512wikieng, Hermes is around 9.5.
46
  - I also measure in French and Serbian to observe the variances.