s1.1 model that is trained jointly with safety reasoning data (STAR-1).
-
BatsResearch/safe-s1.1-7b-sample0.1
Text Generation • 8B • Updated • 13 -
BatsResearch/safe-s1.1-7b-sample0.05
Text Generation • 8B • Updated • 12 -
BatsResearch/safe-s1.1-7b-sample0.25
Text Generation • 8B • Updated • 4 -
BatsResearch/safe-s1.1-7b-sample0.5
Text Generation • 8B • Updated • 6