Hugging Face releases Carbon-X, an open-source, 14B-parameter multimodal AI model to let users query DNA sequences via natural language, trained on 300B tokens (Emily Mullin/Wired)
The new open-source model speaks the language of DNA and can help researchers understand the effects of any changes on gene activity and health.
Hugging Face has released Carbon-X, an open-source, 14B-parameter multimodal AI model designed to allow users to query DNA sequences using natural language. According to Techmeme, the model was trained on 300B tokens and can help researchers understand how changes affect gene activity and health. Business Insider reports the model can both analyze and generate DNA sequences, effectively allowing researchers to "chat" with DNA.
The company developed Carbon-X by training the existing Qwen3-14B language model on genomic sequences and natural language, including DNA from plants, fungi, humans, and other mammals. Business Insider states that Hugging Face worked with research labs in China and Italy on the project. Lewis Tunstall, a senior research scientist at Hugging Face, noted the model could allow a researcher to provide a DNA sequence and ask if a specific mutation might increase a certain effect.
Brief written by urgent.news from Techmeme, Business Insider — 2 reports on this story. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
