Chemistry & ADMET · IBM Research
SMILES transformer pre-trained on 1.1 billion molecules.
1–30s
Runs on On-demand GPU
Runs on our servers with on-demand compute. A first run needs time to load the model; active capacity can be reused and scales down when idle.Run this model
About this model
MolFormer's rotary-attention transformer, trained on the union of ZINC and PubChem, produces molecular representations that transfer to property prediction and similarity search better than fingerprint baselines.
Standardized I/O contract
Every model in the Hub speaks the same contract, which is what lets the Router and the agent call any of them without special-casing.
Inputs
Ligand SMILES
Outputs
Molecular representation.
