Kermt Embed

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.

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 800 per readout, so ~10–20 MB per 1k molecules across the 4 readouts. Plus a small canonical_smiles.npy + validity.npy per run.
• Driver / CUDA: any host supporting CUDA 12.6.

Inputs

Required:

• --csv <path> — SMILES CSV. First column is smiles; other columns are ignored (no targets needed).

Checkpoint (optional — defaults to the released model if omitted):

• --ckpt <path> — any encoder-bearing checkpoint. Grover_base, cmim, hybrid, and finetuned ckpts are all accepted. The validator only refuses ckpts with no encoder. If omitted, the skill offers to download the released pretrained hybrid model nvidia/NV-KERMT-70M-v2 and embed with it — see "Resolve & validate the checkpoint" (workflow step 3).
• --pretrained-release — explicit opt-in to use the released model without the interactive prompt (for non-interactive / agent runs). Mutually exclusive with --ckpt.
• --model-dir <dir> — where to save the downloaded bundle (default $KERMT_REPO/models/NV-KERMT-70M-v2/). An already-complete bundle there is reused, not re-downloaded.

Optional:

• --batch-size N — override the configured default (64).
• --gpus 0 — single GPU id (default 0).
• --from-prepare <dir> — skip the prepare step and reuse an existing prepare_data.json in <dir>.

Workflow

Let $KERMT_REPO be the path to your kermt repo checkout.

1. Pre-flight: container + system probe.

   $KERMT_REPO/agent/scripts/kermt_container.sh check_system

2. Compute run directory.

   RUN_DIR=$KERMT_REPO/runs/embed_$(date -u +%Y-%m-%dT%H-%M-%SZ)

3. Resolve & validate the checkpoint.

   Resolve — only if --ckpt was omitted. Default to the released pretrained hybrid model nvidia/NV-KERMT-70M-v2:

   • Consent gate. Unless --pretrained-release was passed, ask the user: "No checkpoint given — download the released model nvidia/NV-KERMT-70M-v2 (NVIDIA Open Model License, https://huggingface.co/nvidia/NV-KERMT-70M-v2) and embed with it? [y/N]". Never download without an explicit yes (or --pretrained-release). If both --ckpt and --pretrained-release are given, abort — they conflict.
   • Save location. Default $KERMT_REPO/models/NV-KERMT-70M-v2/; honor --model-dir <dir> if given. An already-complete bundle is reused.
   • Download (foreground; ~282 MB on first fetch):

     $KERMT_REPO/agent/scripts/kermt_container.sh run --model-dir <save-dir> -- \
         "python agent/scripts/fetch_released_model.py --out /model"

     Parse the JSON; abort on ok: false (surface errors). On success set <user-ckpt> = <save-dir>/kermt_contrastive_v2.0.pt.

   Validate the resolved (or user-provided) ckpt:

   $KERMT_REPO/agent/scripts/kermt_container.sh run --ckpt <user-ckpt> -- \
       "python agent/scripts/check_checkpoint.py --mode embed --ckpt /ckpt"

   Parse JSON. Abort on ok: false. The validator only refuses encoder-less ckpts (rare).

4. Validate the data.

   $KERMT_REPO/agent/scripts/kermt_container.sh run --data <user-csv> -- \
       "python agent/scripts/check_data.py --mode embed --csv /data/<basename>"

5. Prepare the data (clean-only — no features step).

   $KERMT_REPO/agent/scripts/kermt_container.sh run --data <user-csv> --run-dir $RUN_DIR -- \
       "python agent/scripts/prepare_data.py --mode embed \\
            --csv /data/<basename> --out /runs/data"

   Outputs land at $RUN_DIR/data/prepare_data.json with a single clean_csv path. task/extract_embeddings.py featurizes from SMILES on the fly.

6. Launch the runner (blocking).

   $KERMT_REPO/agent/scripts/kermt_container.sh run \\
       --ckpt <user-ckpt> --run-dir $RUN_DIR -- \\
       "python agent/scripts/run_extract_embeddings.py \\
            --ckpt /ckpt \\
            --prepare-manifest /runs/data/prepare_data.json \\
            --out /runs \\
            [--gpus 0 --batch-size N]"

7. Report to the user.

   • Embeddings directory: $RUN_DIR/out/
     • atom_from_atom.npy, bond_from_atom.npy, atom_from_bond.npy, bond_from_bond.npy (the 4 standard readouts; each shape (N_rows, hidden_size))
     • metadata.pkl — pickle of a dict containing canonical_smiles (RDKit-canonicalized SMILES per row), valid (boolean per-row: did RDKit parse it), plus other run metadata.
   • Manifest: $RUN_DIR/run.json
   • Log: $RUN_DIR/logs/embed.log