News for hackers. Stuff that matters.

agokrani

agokrani on Hacker News

Re:Show HN: DistilKitPlus, a distillation framework between any LLMs on Monday May 05, 2025 @01:33PM (#43897429)
We can distill 14B model to 4B model with performance improvements on AIME24 and GSM8K. We will share our results with a detailed blog post later.