Models, artifacts, and runtimes
Inspect model manifests, versions, artifacts, runtime compatibility, accelerators, and rollout evidence.
What you will practice
List model inventory; Read a model manifest; Compare model versions; Inspect artifact metadata.
Use the worked examples when needed, then test your understanding without them.
- 01List model inventoryA model inventory is an index of artifacts and their intended roles. Identify the active version and retained rollback separately; a listed artifact is not necessarily loaded.Practice
- 02Read a model manifestA manifest records an artifact contract: format, architecture, tokenizer and context assumptions. Read the manifest before selecting a runtime or an inference envelope.Practice
- 03Compare model versionsA version comparison must hold the task and evaluation inputs constant. A better aggregate result from another dataset is not a controlled improvement over the current model.Practice
- 04Inspect artifact metadataArtifact metadata explains what was downloaded or built. Format, size and quantization are useful checks, but an artifact name alone is not a provenance guarantee.Practice
- 05Verify an artifact checksumChecksums detect byte differences relative to a reference. The reference must itself be trusted, and a mismatch should stop activation until its cause is understood.Practice
- 06Match model and runtimeA runtime must support the model architecture and storage format. Insufficient memory and unsupported architecture are different failures and need different responses.Practice
- 07Read context limitsInput tokens and reserved output share a context budget. Check the combined planned use rather than comparing the prompt alone with the limit.Practice
- 08Inspect tokenizer metadataToken IDs depend on the tokenizer paired with the model. A tokenizer mismatch can change segmentation and special tokens even when the input text is identical.Practice
- 09Compare quantization profilesQuantization changes representation and memory use, and it can affect task quality. Measure both resource behavior and held-out quality for the intended workload.Practice
- 10Read memory requirementsWeight size is not the total serving memory requirement. Leave space for the KV cache, runtime buffers and concurrent work before declaring an artifact a fit.Practice
- 11Inspect accelerator availabilityAccelerator availability has several layers: device visibility, driver/runtime support and free memory. A visible GPU does not prove that the model runtime can use it.Practice
- 12Spot a runtime mismatchMismatch diagnosis starts with explicit compatibility evidence. When a runtime rejects an architecture, changing prompt text cannot repair the loader contract.Practice
- 13Choose a rollback artifactA rollback artifact should be known-good, retained and compatible with the current runtime and configuration. The oldest available file is not automatically a safe rollback.Practice
- 14Review model provenanceProvenance connects an artifact to its source, license and revision. Preserve that chain alongside the hash so another operator can explain what was activated.Practice
- 15Build a model baselineA serving baseline includes model, tokenizer, runtime, quantization and workload. Record these together before tuning so changes can be attributed rather than guessed.Practice
- 16Models and runtimes checkpointModel release readiness combines compatibility, capacity and quality evidence. Passing one dimension is not permission to ignore another failed gate.Practice