# Model Artifact

> The trained model file, with its learned weights, that is loaded to serve predictions.

Record: `lexicon:model-artifact`
Kind: artifact
Layer: [Correctness Core](https://banes-lab.com/records/layer/correctness-core.md)
Canonical: https://banes-lab.com/ontology/lexicon#lexicon-model-artifact

Listed in [Lexicon terms](https://banes-lab.com/api/records/lexicon.md), after [Input/Output Contract](https://banes-lab.com/records/lexicon/input-output-contract.md) and before [Model Registry](https://banes-lab.com/records/lexicon/model-registry.md).

## Category

- [Model Architecture](https://banes-lab.com/records/lexicon-category/model-architecture.md)

## Required by

- [Model Inference](https://banes-lab.com/records/architecture/model-inference.md)

## Linked from

- [Model Architecture](https://banes-lab.com/ontology/principles/architecture-category-model-architecture.md)