BioNeMo Recipes (NVIDIA)

github.com/nvidia-bionemo/bionemo-recipes
Active851updated 2 hours ago
Python

TransformerEngine-accelerated checkpoints and training recipes for scaling biological foundation models (ESM-2, AMPLIFY, Geneformer, CodonFM) from single-GPU prototyping to multi-node FSDP training with FP8/MXFP8/NVFP4 precision, compatible with PyTorch, HF Accelerate, and PyTorch Lightning, plus sparse-autoencoder interpretability tools for biological foundation models (851+ stars, 2026)

Sourced from

  • Awesome AI for Sciencegithub.com/nvidia-bionemo/bionemo-recipes
  • GitHubgithub.com/nvidia-bionemo/bionemo-recipes

Related resources

NVIDIA's open-source platform for building and adapting biological AI models at scale, bundling ESM-2, Geneformer, MolMIM and DNA embedding models with recipes for single-GPU to multi-node training (2025)

Active8462 weeks ago
Python

E(3)-equivariant neural network interatomic potentials achieving DFT accuracy with up to 1000× less training data than invariant models, foundational architecture behind MACE and Allegro (Harvard, MIT, Nature Communications 2022)

Active9542 weeks ago
Python
MIT

OpenChem is a deep learning toolkit for Computational Chemistry with PyTorch backend.

Stale7542 years ago
Python
MIT

Highly scalable equivariant deep learning interatomic potentials enabling million-atom molecular dynamics simulations with ab initio accuracy, building on E(3)-equivariant architectures for large-scale atomistic modeling (mir-group, MIT License, 480+ stars)

Active4983 months ago
Python
MIT

Deep learning library for Chemistry based on Tensorflow

Active6.9K3 weeks ago
Python
MIT

Open-source framework for building physics-ML models at scale (renamed from Modulus, 2025)

Active3.2K2 weeks ago
Python
Apache-2.0