
Continues KERMT molecular pretraining on a custom SMILES corpus inside a GPU container
- Open source
- 4K GitHub stars
- Health and science


Continues KERMT molecular pretraining on a custom SMILES corpus inside a GPU container

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

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

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

Fine-tunes public CodonFM Encodon checkpoints on labeled coding-sequence data

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

Finetunes the NV-Generate MR-Brain diffusion model on your own brain MRI volumes

Finetunes NV-Segment-CT VISTA3D on your CT NIfTI image and label datasets

Finetunes the NV-Generate-CTMR MAISI VAE on your own CT or MRI NIfTI datalists

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

Sets up the public CodonFM repo, dev container and Encodon checkpoint downloads
The closest alternatives to Kermt finetune are Kermt continue pretrain, Kermt infer, Kermt pretrain scratch, Kermt embed and Kermt add cmim pretrain.
Yes. Kermt continue pretrain, Kermt infer, Kermt pretrain scratch have a free or open-source option.