Agent skill · nvidia
kermt-infer
Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has task FFN heads (refuses pretrain ckpts with a redirect to kermt-finetune), validates the CSV, prepares the data (clean + rdkit_2d features), then launches main.py predict inside the kermt container (blocking, minutes-scale).
What it needs
About 3k tokens when loaded.
What this skill does
kermt-infer Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill is the workflow orchestrator: validate ckpt, validate CSV, prepare data, launch the runner blocking, return the predictions CSV. Skill and runtime paths Set SKILLDIR to the absolute path of this installed skill directory. Export KERMTREPO as the absolute path to the KERMT checkout used for model execution. The bundled container helper mounts that checkout at /workspace and this skill at /skill (read-only). Commands inside the container use /skill/scripts/; defaults are bundled in config/. Hardware requirements GPUs: 1 (single-GPU). Multi-GPU inference is not currently supported. VRAM: ≥ 4 GB for the default batchsize 32. Disk: a few hundred MB per run (cleaned CSV + features + predictions). Driver / CUDA: any host supporting CUDA 12.6 (the kermt image base). Inputs Required: --ckpt <path> — finetuned checkpoint (must have task FFN heads). The validator refuses pretrain ckpts with a redirect to kermt-finetune. --csv <path> — SMILES-only CSV. First column is smiles; other columns are ignored. Optional: --batch-size N — override the configured default (32). --seed N — random seed for inference (deterministic featurization paths). --gpus 0 — single GPU id (default 0). Multi-GPU rejected. --from-prepare <dir> — skip the prepare step and reuse an existing preparedata.json in <dir>. Workflow Let $KERMTREPO be the path to your kermt repo checkout, and assume kermt-setup has built kermt:latest. 1. Pre-flight: ensure container + system probe. Refuse to proceed on ok: false. 2. Compute run directory. 3. Validate the checkpoint. Parse the JSON. Abort on ok: false. The validator rejects pretrain ckpts (hastaskffn: false) with a redirect to kermt-finetune. 4. Validate the data. Abort on ok: false. 5. Prepare the data. Outputs land at $RUNDIR/data/preparedata.json with cleancsv + cleannpz paths (rdkit2dnormalized features). 6. Launch the runner (blocking). …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nvidia/bionemo-kermt-infer