---
license: apache-2.0
---

Llama 2 7B quantized with AutoGPTQ V0.3.0.

* Group size: 32
* Data type: INT4

This model is compatible with the first version of QA-LoRA.

To fine-tune it with QA-LoRA, follow this tutorial:
[Fine-tune Quantized Llama 2 on Your GPU with QA-LoRA](https://kaitchup.substack.com/p/fine-tune-quantized-llama-2-on-your)