# RuntimeError: PEFT adapter 'my_adapter' not found in checkpoint. Available adapters: ['base', 'lora_v1']

- **ID:** `huggingface/peft-adapter-not-found-in-checkpoint`
- **Domain:** huggingface
- **Category:** config_error
- **Verification:** ai_generated
- **Fix Rate:** 92%

## Root Cause

The requested PEFT adapter name does not match any adapter stored in the checkpoint directory or merged model.

## Version Compatibility

| Version | Status | Introduced | Deprecated |
|---------|--------|------------|------------|
| huggingface/peft 0.9.0 | active | — | — |
| huggingface/peft 0.10.0 | active | — | — |
| huggingface/transformers 4.38.0 | active | — | — |

## Workarounds

1. **List available adapters and load the correct one: `model.load_adapter('lora_v1')` or `PeftModel.from_pretrained(model, 'path/to/checkpoint', adapter_name='lora_v1')`** (95% success)
   ```
   List available adapters and load the correct one: `model.load_adapter('lora_v1')` or `PeftModel.from_pretrained(model, 'path/to/checkpoint', adapter_name='lora_v1')`
   ```
2. **If loading a single adapter, use `PeftModel.from_pretrained(model, 'path/to/checkpoint')` without specifying adapter_name, which defaults to 'default'.** (85% success)
   ```
   If loading a single adapter, use `PeftModel.from_pretrained(model, 'path/to/checkpoint')` without specifying adapter_name, which defaults to 'default'.
   ```

## Dead Ends

- **Rename the adapter folder to 'my_adapter' manually** — PEFT uses internal metadata to track adapter names; renaming the folder without updating the metadata file (adapter_config.json) causes a mismatch. (80% fail)
- **Set `load_in_8bit=True` to bypass adapter loading** — Loading in 8-bit doesn't skip adapter loading; it still tries to find the adapter and fails with the same error. (90% fail)