AnalysisAI ModelsNovember 17, 2026

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

Read original source →huggingface.co

The harness-hub Qwen3.8-27B-pi-adapted LoRA (rank 32, ~640 MB) raises SWE-bench Pro (hard 51) pass@1 from 39.2% to 64.7% and Terminal-Bench 2.1 from 39.5% to 55.8% inside the pi harness. With thinking off it matches the base model's max-effort accuracy using ~4.5x fewer tokens.

How this story unfolded

2 days · 3 reports · 7 community posts · 10 of 12 shown

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

More stories today

Open the live feed