FineDNA midtraining lifts DNA scores without degrading English
LoubnaBenAllal1 · x · 2026-11-01
With the right learning rate, midtraining Qwen3-14B on FineDNA keeps improving DNA scores (sequence recovery 0.56, ClinVar variant-effect AUROC 0.92) while English performance holds at the starting level. The recipe is open-sourced.
Related event: FineDNA midtraining proves essential for RL on DNA tasks(2 posts)→
More from Research
- HuggingFace releases FineDNA dataset, turning Qwen3-14B into a DNA model that beats GPT-6.1 — loubnabnl · 2026-11-01
- If your AI scores 100%, your eval is wrong — an AI safety researcher's eval playbook — AI Engineer · 2026-11-01
- Control Vectors experiment: letting an agent manage its own activations — sloppenheimer · 2026-11-01
- FlashRSI open-sources RSI research: 12 algorithms, 30+ benchmarks, OOD gains still elusive — HuaxiuYaoML · 2026-11-01
- Claude designed scorpion toxin binders: 17 of 211 lab-tested designs bound — shoumikgoswami · 2026-11-01
- Carbon-X: midtrained Qwen3-14B beats every open LLM on DNA benchmarks — LoubnaBenAllal1 · 2026-11-01