---
library_name: peft
---
## Training procedure

This adapter has been fine-tuned using quantization-aware LoRA (QA-LoRA). 

More details on the training procedure here: [Fine-tune Quantized Llama 2 on Your GPU with QA-LoRA](https://kaitchup.substack.com/p/fine-tune-quantized-llama-2-on-your)


The base model was quantized with AutoGPTQ INT4. You can find it here:

[kaitchup/Llama-2-7b-4bit-32g-autogptq](https://huggingface.co/kaitchup/Llama-2-7b-4bit-32g-autogptq)


### Framework versions


- PEFT 0.4.0