maltefranke/morph
https://huggingface.co/maltefranke/morphCheckpoints for unconditional 3D molecular generation on QM9, GEOM-Drugs and ChEMBL3D, GEOM-Drugs N-conditional generation, GEOM-Drugs and QM9 logP-conditional generation, GEOM-Drugs scaffold decoration, and CrossDocked scaffold decoration in protein pockets.
Sourced from
- HuggingFace — maltefranke/morph
Related resources
ChatterjeeLab/CupOFMoCA
by ChatterjeeLabCode, model weights, configurations, and reported outputs for CupOFMoCA: Coupled Objective-Guided Discrete Flows for Molecular Conjugate Assembly (NeurIPS 2026).
akhljndl/smollm
by akhljndlA 53K-parameter weight-shared transformer that learns SMILES grammar by applying one small block 8 times. It reaches 95.3% validity on ZINC-250K — outperforming an unshared GPT 10× larger (87.6%).
the-matter-lab/clari
by the-matter-labThis repository contains data and checkpoints for the paper: Fast Organic Crystal Structure Prediction with Unit Cell Flow Matching (arXiv).
valencelabs/mars-fm
by valencelabsThis repository contains the PyTorch model weights for MarS-FM (Markov Space Flow Matching) trained on the MD-CATH dataset. This model was introduced in the ICLR 2026 paper: MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models.
State-of-the-Art Geometric GNN for Predicting Molecular Properties
MolReactGen is a model that generates reaction templates in SMARTS format (this model) and molecules in SMILES format.