AnalysisAI ModelsNovember 17, 2026

Hugging Face LoRA adapter lifts Qwen3.8-27B coding scores

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. It lifts SWE-bench Pro (hard 51) from 39.2% to 64.7% and Terminal-Bench 2.1 from 39.5% to 55.8%, with thinking off and ~4.5x fewer tokens.

How this story unfolded

2 days · 3 reports · 8 community posts · 11 of 13 shown

  1. Nov 17
  2. Nov 18
  3. Nov 19

More stories today

Open the live feed