Hugging Face releases open Carbon-X model for chatting with DNA

Hugging Face has released Carbon-X, an open-source 14-billion-parameter model trained on genomic sequences and natural language that answers questions about how DNA changes affect gene activity and health. It runs locally on a laptop and processes sequences of roughly 50,000 base pairs at a time.

• 14-billion-parameter model trained on 300 billion DNA and text tokens
• Handles sequences of roughly 50,000 base pairs per query
• Runs locally, with no data sent to Hugging Face
• Accuracy not yet validated in wet lab experiments