adamo1139 commited on
Commit
f5fe2d2
1 Parent(s): 1a2060e

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ Will write a proper model card later.
2
+
3
+ It's Mistral 7B v0.1 finetuned on MaziyarPanahi/magpie-ultra-v0.1-sharegpt for one epoch. GaLore full training. ChatML prompt format. It needs non-zero rep_p sampling, around 1.05. Took around 16 hours on 3090 Ti.