LoRA Adapters - RunAnywhere Documentation

A LoRA adapter specialises a base model without swapping it out. The base model stays loaded throughout, so switching behaviour costs far less than switching models. On a phone that difference is the whole point.

await RunAnywhere.lora.apply('legal-summarizer')

const result = await RunAnywhere.llm.generate('Summarize this clause: …')

await RunAnywhere.lora.remove('legal-summarizer')

The namespace

lora.apply(adapterId: string, scale?: number): Promise<void>
lora.remove(adapterId: string): Promise<void>
lora.removeAll(): Promise<void>
lora.list(): Promise<LoraState>

Scale

scale controls how strongly the adapter pulls the base model. Leave it unset for the adapter’s own default. Lower values blend the adapter with base behaviour; higher values commit to it. If output degrades after applying an adapter, scale is the first thing to turn down.

Removing

await RunAnywhere.lora.remove('legal-summarizer')
await RunAnywhere.lora.removeAll()

Removal is keyed by adapter id.

Switching adapters

Adapters stack. Remove before applying another, or two of them fight and the output is worse than either alone.

async function useAdapter(id: string): Promise<void> {
  await RunAnywhere.lora.removeAll()
  await RunAnywhere.lora.apply(id)
}

The base model has to support it

An adapter is trained against a specific base model. Applying one to a different base either fails or produces nonsense. Check the model’s supportsLora flag before offering adapters in your interface. React Native exposes the short form only. Catalog management is available on the Swift and Electron SDKs.