# LoRA adapters

> Register a LoRA adapter trained on Qwen3 8B from Hugging Face, add up to 4 to your own Qwen3 8B endpoint, and call each one by its id at no extra cost.

Source: https://bitsrun.com/docs/models/adapters/
Updated: 2026-11-11

A LoRA adapter is a small file that changes how a base model answers: your task, your tone, your format. It is far smaller than the model itself, so one endpoint can serve the base model and several adapters at once.

## What we accept

- **Base model:** Qwen3 8B. In `adapter_config.json`, `base_model_name_or_path` must be `Qwen/Qwen3-8B` (or a copy such as `unsloth/Qwen3-8B`).
- **Plain LoRA** with rank (`r`) up to 64, on any of `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj` and `down_proj`. No DoRA, no prompt tuning, no extra trained layers (`modules_to_save`), no per-layer settings.
- **Files:** `adapter_config.json` and `adapter_model.safetensors` at the top of the repo, up to 1 GB. Adapters saved only as `.bin` files are refused; PEFT's `save_pretrained` writes safetensors by default.

## Register an adapter

1. Open **Adapters** in the dashboard and select **Register adapter**.
2. Choose where it is:
   - **On Hugging Face:** type `hf:owner/repo` or paste the repo page.
   - **Upload a folder:** choose the folder PEFT saved. Only `adapter_config.json` and `adapter_model.safetensors` are sent; notes such as `README.md` stay on your computer. A folder with `.bin` or other weight files is refused before anything uploads.
3. Add a label if you like, then select **Register adapter** (or **Upload and register**). We check the config first, then copy the files into your storage, usually in under a minute. The row shows **Ready** when it is done.

We use the repo's latest version at that moment and keep it fixed. Private and gated repos need your Hugging Face token, see [Gated and private repos](https://bitsrun.com/docs/models/gated-repos/). An adapter counts toward your storage like an upload, see [Model storage](https://bitsrun.com/docs/billing/storage/). An account holds up to 10 adapters.

## Add adapters to an endpoint

Adapters run on your own endpoint deployed from `hf:Qwen/Qwen3-8B-FP8` or `hf:Qwen/Qwen3-8B` (served by vLLM).

- **New endpoint:** after **Check model**, choose up to 4 ready adapters under **Adapters**.
- **Existing endpoint:** select **Performance**, choose adapters under **Settings**, then **Review changes** and **Apply settings**. The endpoint restarts on its next request with the new set.

Their memory comes out of the endpoint's memory length, so a long context may get a little shorter. See [Performance settings](https://bitsrun.com/docs/endpoints/performance/).

## Call an adapter

Send the adapter's id (it starts with `lora-`) as `model` to your endpoint's URL. Any other model name answers with the base Qwen3 8B.

```bash
curl https://<endpoint-id>.endpoint.bitsrun.com/v1/chat/completions \
  -H "Authorization: Bearer $BITSRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "lora-<adapter-id>", "messages": [{"role": "user", "content": "Hello"}]}'
```

The **Adapters** page shows this sample with your own endpoint URL and adapter id.

## Price

Adapters on your endpoint cost nothing extra: you pay the endpoint's GPU price by the second while it runs, as always.

## Delete an adapter

Remove it from every endpoint that uses it first (in Performance), then select **Delete** on its row. Its files leave your storage at once.

## What can go wrong

| Message says | What to do |
|---|---|
| This adapter was trained on a model we do not serve adapters for | Train on Qwen3 8B, or fix `base_model_name_or_path`. |
| This adapter's rank is above 64 | Train again with `r` set to 64 or less. |
| We serve plain LoRA adapters | Train a plain LoRA without DoRA, `modules_to_save` or per-layer settings. |
| We need adapter_config.json and adapter_model.safetensors | Save the adapter again with PEFT and push both files to the top of the repo. |
| One of your endpoints uses this adapter | Remove it in that endpoint's Performance settings, then delete it. |
| Adapters work on endpoints that run Qwen3 8B with vLLM | Deploy `hf:Qwen/Qwen3-8B-FP8` for your adapters. |