> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getimpala.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# LoRA adapters

> Serve your fine-tuned model on Impala. Bring a LoRA adapter, and we deploy it for you to call through serverless or batch.

Impala serves models fine-tuned with **LoRA** (low-rank adaptation). You bring the adapter, we deploy it with its base model, and you send requests to it through serverless or batch.

## What to send us

Either form works:

* **A separate adapter**, alongside the name of the base model it was trained on.
* **A merged model**, with the adapter weights already folded into the base model.

Contact your Impala account team to share it.

## How it's served

The adapter is loaded with the model when it's deployed, so every request to that deployment uses it. Switching adapters per request isn't supported yet.

## Sending requests

Send requests exactly as you would. See [Chat completions](/send-a-request) for serverless and [Run a batch](/run-your-first-batch) for batch.

If you retrain full weights often, [Impala Leap](/weight-sync) swaps new checkpoints onto a running deployment without a redeploy.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.