all 7 comments

sorted by: hot top controversial new old
[–] [S] 3 points 2 months ago (1 child)

I feel like Ornith 1.0 9b was the best coding model at that size (since Qwen has neglected that size). Maybe now Ling Tiny is better but I'm curious to try Ornith 1.5

  • source
  • hideshow 1 child comment
  • [–] 2 points 2 months ago

    I agree. I'm very interested to try it. I felt like Ornith 1.0 tried a little too hard to second-guess and overcorrect itself and would sometimes end up steering itself down an inescapable rabbit hole of self-correction ad absurdum, when ironically its first solution was often the best, sometimes would work as-is or with only a little refinement needed. I'm hopeful that 1.5 will improve that.

  • source
  • parent
  • [–] 1 point 2 months ago (4 children)

    My previous experience with finetunes is bad..

    Today I tried Ornith-1.5-35B-A3B, and I'm quite positively surprised by it.. I compared it to both Qwen3.7-Flash and MiMo-V2.5 (via OpenRouter) in a few coding tasks and Ornith seems to be better than both! Thinks much more but the result definitely speaks for itself.

    Hoping for Qwen3.8-35B soon 🤞

  • source
  • hideshow 4 child comments
  • [–] [S] 2 points 2 months ago (2 children)

    Have you tried Kat Coder? It's also a fine-tune of Qwen 35b and I've heard good things about it

  • source
  • parent
  • hideshow 2 child comments
  • [–] 3 points 2 months ago (1 child)

    Yeah I tried Kat Coder when it came out, I don't remember the exact issue I ran into but I identified a definite regression in my specific use cases compared to using vanilla. Ornith seems to be equivalent or better so far 👍

  • source
  • parent
  • hideshow 1 child comment