Hugging Face presenta Carbon-X, un modelo de lenguaje de ADN abierto de 14B que une por primera vez el ADN y el lenguaje natural

Este es el extracto disponible del feed. Puede estar abreviado o en el idioma original.

Hugging Face has released Carbon-X, an open DNA language model with 14.8B parameters. Carbon-X is a decoder-only model from Hugging Face Bio. It reads raw DNA in a chat and answers in English. It predicts whether mutations are benign or pathogenic, flags regulatory regions, classifies organisms and predicts next bases. The weights ship under Apache 2.0, so labs can keep sensitive sequences on their own GPUs. Hugging Face built it with Zhongguancun Academy and TIGEM / University of Naples Federico II. TL;DR Size: 14.8B parameters (dense, no MoE), 40,960-token context. Runs on: 1 x 80 GB GPU in bfloat16 via vLLM or Transformers. Official GGUF: Q8_0 is 15.8 GB, Q4_K_M is 9.6 GB. Performance: 66.7% average on 5 DNA benchmarks, best of every open model tested (self-reported). Best: 74.9% on BioReason Coding, ahead of every model tested, open or closed. Worst: 29.8% on GenomeQA splice-site questions. What is Carbon-X and how does it work? Carbon-X starts from Qwen3-14B. DNA and text share 1 token stream in 1 decoder. There is no separate DNA encoder, unlike earlier work such as BioReason. The key structure piece is a hybrid tokenizer. It keeps Qwen3’s BPE vocabulary for text and adds 5,515 DNA tokens. These include 4,096 non-overlapping 6-mers, 1,364 tail tokens and 3 markers. One DNA token covers 6 base pairs. DNA runs of 6 or more A/C/G/T bases are tagged automatically. The backbone is a standard Qwen3 stack. It has 40 layers, hidden size 5120 and GQA with 8 KV heads. How was Carbon-X trained? Training ran in four stages, per the model card: Embedding warmup: about 10B tokens with the transformer frozen, so only the new DNA embeddings learn. Mid-training: 302B tokens at 8,192 sequence length. The mix is 55% raw DNA, 20% English, 15% biology text and 10% instruction data. SFT: 3 epochs over 20 dataset subsets, with responses checked by deterministic verifiers built with domain experts. RL: asynchronous GRPO with verifiable rewards over 2 rounds, using TRL