Commit History

Refresh README; document sft-c16 (latent-only reasoning, c=16, learned stop)
3129e95
verified

nmitchko commited on

Update README.md
5c66a36
verified

nmitchko commited on

Update README.md
7311e53
verified

nmitchko commited on

Add CoLaR reasoning head (SFT + GRPO), model card, and technical report
84b9eca
verified

nmitchko commited on