‹ BackHN Continuity

Thread

Clef: Open-weight decision models, and new RL fine-tuning platform

637 points · 217 comments · jasondavies

  1. bityard · · focus · HN ↗
    Clef is based on Qwen3.8-27B and Clef-flash is based on Qwen3.8-9B (edit: actually Qwen3.5-9B). So, similar in spirit to Kev by my understanding, but based on a newer model.
    1. NitpickLawyer · · focus · HN ↗
      > and Clef-flash is based on Qwen3.8-9B

      There is no official qwen 3.8 9b

      From the model card:

      > Clef-Flash is post-trained from Qwen/Qwen3.5-9B. See Clef for the larger variant.

      1. ddarolfi · · focus · HN ↗
        It's based on Qwen3.5-9B, maybe a typo
        1. verdverm · · focus · HN ↗
          I've been guilty of the same wishful projection
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.