
Pretrains a KERMT molecular model from scratch on your own SMILES corpus
- Open source
- 4K GitHub stars
- Health and science


Pretrains a KERMT molecular model from scratch on your own SMILES corpus

Finetunes a pretrained KERMT molecular encoder on your labeled SMILES CSV in Docker

Runs predictions with a finetuned KERMT checkpoint on a SMILES-only CSV

Extracts per-molecule embeddings from KERMT checkpoints in a containerized GPU run

Converts a GROVER checkpoint into a hybrid cMIM model and continues pretraining it

Guides writing and debugging GPU-accelerated RDKit cheminformatics code with nvMolKit

Generates and optimizes small molecules from a seed SMILES using NVIDIA's MolMIM NIM

Fine-tunes Parakeet TDT ASR on clinical vocabulary and measures the gain offline

Guides an agent to build and change NVIDIA ALCHEMI Toolkit atomistic simulation and MLIP

Generates novel drug-like molecules with the GenMol NIM microservice

Sets up the public CodonFM repo, dev container and Encodon checkpoint downloads

Fine-tunes public CodonFM Encodon checkpoints on labeled coding-sequence data
The closest alternatives to Kermt continue pretrain are Kermt pretrain scratch, Kermt finetune, Kermt infer, Kermt embed and Kermt add cmim pretrain.
Yes. Kermt pretrain scratch, Kermt finetune, Kermt infer have a free or open-source option.