Hugging Face open-sources Carbon-A-1.2B, a DNA model for coding-region annotation
lmoroney · x · 2026-10-12
Hugging Face's new open model Carbon-A-1.2B (Apache 2.0) marks protein-coding bases in eukaryotic genomes: six-letter DNA tokens, 98,304 bp windows, two classification heads (one per strand) to catch overlapping coding regions, trained on 2,055 RefSeq assemblies with confidence scores per predicted gene. Runs via Transformers on PyTorch; the model card includes a yeast walkthrough with nucleotide F1 of 0.998.
More from Research
- Work2Skill Turns Human GUI Demos into Reusable Agent Skills, Beating No-Skill Baselines — nex-agi · 2026-10-12
- TouchScale: 500-Hour Vision-Tactile Dataset Lifts Robot Manipulation Success from 22.5% to 57.5% — 2077AIDataFoundation · 2026-10-12
- UCSD paper bakes theory of mind into RL reward, letting a 7B agent model partners solo — rohanpaul_ai · 2026-10-12
- All of Science Embedded: 203M Papers Free for AI Agent Search — evilsocket · 2026-10-12
- Physics law sets diffusion model's noise schedule for better particle spread prediction — bravo_abad · 2026-10-12
- Decision Index 0.3.1: vLLM d3 and Mapika Decider 31B tie for #1 — multimodalart · 2026-10-12