HyenaDNA

Long-range genomic foundation model, pretrained at single-nucleotide resolution on context lengths up to 1 million tokens.

Unsigned

Overview

HyenaDNA is a long-range genomic foundation model from the Hazy Research lab at Stanford, pretrained at single-nucleotide resolution on context lengths of up to 1 million tokens, substantially longer than prior genomic language models. It is released as a family of checkpoints (tiny/small/medium/large) at varying sequence lengths.

**Licence note**: the Hugging Face model card page does not surface a licence tag in its rendered content; the licence stated here (Apache-2.0) was confirmed directly against the `LICENSE` file in the model's source repository, `github.com/HazyResearch/hyena-dna`, not assumed.

**Registry note on `model_card_uri`**: this points to the model's standard Hugging Face model card, not a GA4GH Genomic AI Model Card v0.6.0-formatted document. No model has yet published a card in the GA4GH v0.6.0 format, since it is a newly drafted specification.

Details

Licence: Apache-2.0
Version: large-1m-seqlen
Category: Genomic foundation model
Homepage: https://huggingface.co/LongSafari/hyenadna-large-1m-seqlen-hf
Repository: https://github.com/HazyResearch/hyena-dna
Maintainers: Susheel Varma (@susheel, GA4GH AI Workstream / Sage Bionetworks)
Keywords: dnagenomicsfoundation-modellong-rangesingle-nucleotide-resolution

Safety classification

No safety classification has been submitted for this entry.

Model Card

View the full GA4GH Genomic AI Model Card ↗

Hosting: huggingface
Access: https://huggingface.co/LongSafari/hyenadna-large-1m-seqlen-hf

Mirrored data last synced from the Model Card at 2026-09-04T11:05:00.000Z. See the linked card for the authoritative, live version.

Provenance

Created: 2026-09-04T11:05:00.000Z
Updated: 2026-09-04T11:05:00.000Z
Last verified: 2026-09-04T11:05:00.000Z