LaunchAI ModelsNovember 17, 2026

Hugging Face LoRA lifts Qwen3.8-27B coding success from 39% to 65%

Read original source →huggingface.co

Hugging Face's harness-hub released Qwen3.8-27B-pi-adapted, a rank-32 LoRA trained with RL to drive the pi coding agent: SWE-bench Pro (hard 51) pass@1 rose 39.2% to 64.7%, Terminal-Bench 2.1 39.5% to 55.8%. With thinking off it matches the base model's max-effort accuracy using ~4.5x fewer tokens.

How this story unfolded

1 day · 2 reports · 6 community posts · 8 of 10 shown

  1. Nov 17
  2. Nov 18

More stories today

Open the live feed