Post
2687
KAT-V1 đĽ a LLM that tackles overthinking by switching between reasoning and direct answers, by Kuaishou.
Kwaipilot/KAT-V1-40B
⨠40B
⨠Step-SRPO: smarter reasoning control via RL
⨠MTP + Distillation: efficient training, lower cost
Kwaipilot/KAT-V1-40B
⨠40B
⨠Step-SRPO: smarter reasoning control via RL
⨠MTP + Distillation: efficient training, lower cost