rewire.it
model · family

Evo 2

Evo 2 models and generates DNA at nucleotide resolution using the StripedHyena 2 architecture.

0 evaluations · 0 metric rows

At a glance

Explanatory profile: source reviewed · Automated source review, 2026-09-16. This does not change the review status of its results.

Inputs, outputs and configuration
PropertyDescription and evidence
Training resourceOpenGenome2ArcInstitute/evo2 official source · README.md: introduction, Models and Installation
ObjectiveAutoregressive sequence predictionArcInstitute/evo2 official source · README.md: introduction, Models and Installation
Configuration in this record7BArcInstitute/evo2 official source · README.md: introduction, Models and Installation
Context limitsNot extracted or verified for this record.
AccessNot extracted or verified for this record.
Code licenceNot extracted or verified for this record.
Weights licenceNot extracted or verified for this record.

How it works

Conceptual procedure

Schematic of the documented input, computation and output; not an executable configuration.

Conceptual procedureDNA nucleotides. Then: StripedHyena 2. Then: Autoregressive predictions. Then: Sequence scoring or generationDNA nucleotidesStripedHyena 2Autoregressive predictionsSequence scoring or generation
Read the diagram as text
  1. DNA nucleotides
  2. StripedHyena 2
  3. Autoregressive predictions
  4. Sequence scoring or generation
ArcInstitute/evo2 official source · README.md: introduction, Models and Installation

An autoregressive sequence model predicts successive nucleotides from preceding context. Scoring and generation use the selected released checkpoint; context length and device requirements depend on that configuration.

ArcInstitute/evo2 official source · README.md: introduction, Models and Installation

Benchmarks and results

Release 2026-09-16-d74d282221a9 · 0 evaluations · 0 metric rows. Different protocols are not a single leaderboard.

No evaluations linked in this release.

Strengths and limitations

Strengths supported by sources

  • The family is designed for long-context sequence modelling, with released inference code.ArcInstitute/evo2 official source · README.md: introduction, Models and Installation

Limitations and conditions

  • A family-level maximum context length does not establish the settings used by a particular published evaluation.ArcInstitute/evo2 official source · README.md: introduction, Models and Installation
Profile review details

Primary project documentation or paper inspected for the explanatory claims and cited locations. Reviewed coverage concerns this narrative, not complete metadata, independent reproduction or a performance ranking.

Stable record: catalog-model-evo-2

Sources and history

Release 2026-09-16-d74d282221a9 · Record review: discovered

Download this release
Technical metadata and extraction receipts

Stable ID: catalog-model-evo-2

areas
dna-genomes; microbes-communities
method types
foundation model
entity level
family
version
7B
reported name
Evo 2
access
Public checkpoints; official local inference needs CUDA hardware and substantial memory.
method type
foundation model
missing metadata
checkpoint revision: not_yet_extracted; training data: not_yet_extracted; licence: not_yet_extracted
Related records

    Suggest a correction