Kimi K1.5: Scaling Reinforcement Learning with LLMs

Re:Kimi K1.5: Scaling Reinforcement Learning with LLMs by joaohkfaria on Tuesday January 21, 2025 @09:31AM (#42780468)

But wait, which LLM models were used to train Kimi? It wasn't clear on the report.

[ Parent | on HN ]

Re:Kimi K1.5: Scaling Reinforcement Learning with LLMs by m00x on Wednesday January 22, 2025 @07:20PM (#42799049)

wdym? They did their own pretraining.

[ Parent | on HN ]