CNWPlayer
/

VegaLM1-42M-Base

Model card Files Files and versions

CNWPlayer commited on Aug 22

Commit

dcf57eb

·

verified ·

1 Parent(s): 6ff151c

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ Note: AI was used in the creation of this project. But that's why you're here, i
 This is the base model for VegaLM1-42M, an experimental SLM trained on various corpi... corpuses... datasets.
 It's not Fable 6, but it's good enough, ok?
-Evals for the 262M tok checkpoint:
 - BananaMind Base Bench 1.1: 132/350 (37.71%), Elo 912.8, roughly on par with 10M models
-The first 262M tokens the model saw came from a 100M selection of fineweb-edu

 This is the base model for VegaLM1-42M, an experimental SLM trained on various corpi... corpuses... datasets.
 It's not Fable 6, but it's good enough, ok?
+Evals for the 235M tok checkpoint:
 - BananaMind Base Bench 1.1: 132/350 (37.71%), Elo 912.8, roughly on par with 10M models
+The first 235M tokens the model saw came from a 90M selection of fineweb-edu