HuggingFace Open-Sources FineDNA, 14B Model Tops DNA Benchmarks
HuggingFace's biology team released FineDNA, a 300B+ token genomic dataset, along with the full recipe for training Carbon-X, a Qwen3-14B-based model that surpasses GPT-6.1 on DNA benchmarks and becomes the strongest open-source language model for the domain.
2026-11-01 ~ 2026-11-01 · 2 related posts
- Episode 1: Hugging Face Open-Sources DNA Model Carbon-X as Stanford Professor Questions Its Benchmarks(2026-10-22, 33 posts)
- Episode 2: Hugging Face Open-Sources Carbon-X, a 14.8B DNA Language Model(2026-10-25, 3 posts)
- Episode 3: HuggingFace Open-Sources FineDNA, 14B Model Tops DNA Benchmarks(2026-11-01, 2 posts)
- Episode 4: Hugging Face open-sources Carbon DNA foundation models(2026-11-01, 2 posts)
- Hugging Face releases FineDNA: 300B+ token dataset to teach LLMs DNA — LoubnaBenAllal1 · 2026-11-01
- HuggingFace releases FineDNA dataset, turning Qwen3-14B into a DNA model that beats GPT-6.1 — loubnabnl · 2026-11-01