Kermt Embed
Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint.
Install
npx skills add NVIDIA/skills --skill kermt-embed -g -a claude-code -y- Repository
- NVIDIA/skills3.8k
- Category
- AI and agents
- Updated
- 5d ago
- License
- Apache-2.0
- Context cost
- Mediumabout 1,726 tokens
- Runs scripts
- Yes, review before use
What it does
Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized embedding extraction and write model bundles, per-readout .npy embeddings, canonical SMILES, and validity arrays to user-selected host directories.
kermt-embed
Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint.
The skill is the workflow orchestrator: validate ckpt, validate CSV, clean
SMILES, launch the runner blocking, return the per-readout .npy files.
Skill and runtime paths
Set SKILL_DIR to the absolute path of this installed skill directory. Export
KERMT_REPO 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/.
See Released models for checkpoint bundle requirements.
Downloads and local outputs
The optional released-model branch reads config/released_model.json for the
Hugging Face repository, pinned revision, and filenames. The bundled
scripts/fetch_released_model.py downloads the model bundle over HTTPS into
the host directory the user selects. Public models work without credentials;
if HF_TOKEN is set, the container helper forwards it for Hugging Face
authentication. Prepared data, logs, and workflow results go into the chosen
run directory.
Hardware requirements
- GPUs: 1 (single-GPU).
- VRAM: ≥ 4 GB for the default
batch_size 64. - Disk: depends on output size, roughly a few MB per 1k molecules at
hidden 800per readout, so ~10, 20 MB per 1k molecules across the 4 readouts. Plus a smallcanonical_smiles.npy+validity.npyper run. - Driver / CUDA: any host supporting CUDA 12.6.
Inputs
Required:
--csv <path>, SMILES CSV. First column issmiles; other columns are ignored (no targets needed).
Checkpoint (optional, defaults to the released model if omitted):
