Command
vraven dataset
Explain a bounded sample cohort and build a reasoning-fingerprint atlas
Minimal form
vraven dataset <model>Arguments and options
| Option | Meaning | Default |
|---|---|---|
model | PyTorch model file | None |
--model-format | Model storage format. VRAVEN instrumentation supports state_dict and trusted pickle models; TorchScript can be loaded but cannot expose PyTorch hooks. | state_dict |
--model-factory, --factory | Import path such as my_project.models:Classifier | None |
--factory-kwargs | JSON object passed to the model factory | {} |
--state-dict-key | — | None |
--strip-prefix | — | None |
--device | — | cpu |
--non-strict | — | False |
--trusted-model | Allow Python-pickle model loading | False |
--input | Batched tensor input file | None |
--labels | Optional per-sample target labels | None |
--mode | — | fast |
--class-names | Comma-separated class labels | None |
--max-samples | — | 128 |
--fingerprint-dimensions | — | 128 |
--max-layers | — | 256 |
--max-units | — | 128 |
--output | — | vraven_dataset_atlas.json |
Exact local helpRun
vraven dataset --help against your installed version before automating a release workflow.