> Canonical page: https://posttrainllm.com/learn/artifacts/lora-specialist

Buildable artifact · stage 3

# LoRA specialist adapter

A narrow adapter built from a frozen base, traceable data, explicit LoRA geometry, and a held-out task gate.

**Readiness**
 recipe contract

**Kind**
 adapter

**Workload**
 fresh training requires an explicit budget

**Stage**
 Change model behavior

## Artifact contract

A narrow adapter built from a frozen base, traceable data, explicit LoRA geometry, and a held-out task gate.

This adapter is classified as recipe contract. Workload guidance: fresh training requires an explicit budget.

## Build

Prepare supervised rows and run the retained SFT path against a frozen base.

## Modify

Change the target data or modules while keeping the baseline and holdout frozen.

## Tune

Vary rank, alpha, target modules, learning rate, or steps from the checked starting profiles.

## Prove

Compare target gain, breadth, safety, latency, RAM, and throughput to the unchanged base.

## Package

Bind adapter, base identity, prompt contract, recipe, and evidence into a specialist package.

## CLI surface

- Run: posttrainllm prep-data
- Run: posttrainllm sft
- Run: posttrainllm eval-gate
- Run: posttrainllm export-mlx

## How to read this dossier

This canonical page separates the retained repository decision from the material that informed it. A source may describe an external claim, historical measurement, local observation, or planned procedure; those evidence classes are not interchangeable. Follow the provenance links before reusing a number or method.

Status and disposition describe what PostTrainLLM retained when this record was indexed. They are not a live product promise, a newly run benchmark, or permission to restart historical work. Unknown or unmeasured fields remain unknown rather than being treated as zero.

To reuse the record, first name the exact claim you need and trace it to the linked source. Then check whether the original environment, model revision, data split, evaluator, hardware, and budget match the proposed use. If they do not, treat the record as a hypothesis or design reference and run the smallest fresh comparison that can falsify it. Preserve negative outcomes and regressions beside any improvement; a local win on one slice does not silently become a general capability claim.

## Source provenance

The normalized record comes from docs/learn/artifact-journey.json . The links below are the tracked evidence and explanatory sources preserved with the record.

- [native-mac/Sources/TinyGPT/SFT.swift ↗](https://github.com/PostTrainLLM/posttrainllm/blob/main/native-mac/Sources/TinyGPT/SFT.swift)
- [docs/recipes/registry.json ↗](https://github.com/PostTrainLLM/posttrainllm/blob/main/docs/recipes/registry.json)
- [Prepare supervised rows and run the retained SFT path against a frozen base. ↗](https://posttrainllm.com/docs/training/sft/)
- [Change the target data or modules while keeping the baseline and holdout frozen. ↗](https://posttrainllm.com/docs/recipes/from-traces/)
- [Vary rank, alpha, target modules, learning rate, or steps from the checked starting profiles. ↗](https://github.com/PostTrainLLM/posttrainllm/blob/main/configs/lora.json)
- [Compare target gain, breadth, safety, latency, RAM, and throughput to the unchanged base. ↗](https://posttrainllm.com/docs/factory/eval-protocol/)
- [Bind adapter, base identity, prompt contract, recipe, and evidence into a specialist package. ↗](https://posttrainllm.com/docs/factory/packaging/)

[Read the Markdown equivalent →](https://posttrainllm.com/learn/artifacts/lora-specialist.md)

Related evidence

- learning path [Change model behavior](https://posttrainllm.com/learn/paths/post-training)
- recipe [Specialist distillation](https://posttrainllm.com/recipes/distillation)
- recipe [Evolution strategies](https://posttrainllm.com/recipes/evolution-strategies)
- recipe [LoRA, DoRA, and adapter geometry](https://posttrainllm.com/recipes/lora)
- recipe [Parameter-efficient fine-tuning variants](https://posttrainllm.com/recipes/peft-variants)

 Canonical record learning-artifact:lora-specialist