| 4-bit GPTQ quantization of [VicUnlocked-alpaca-65b](https://huggingface.co/Aeala/VicUnlocked-alpaca-65b-QLoRA) | |
| **Important Note**: While this is trained on a cleaned ShareGPT dataset like Vicuna used, this was trained in the *Alpaca* format, so prompting should be something like: | |
| ``` | |
| ### Instruction: | |
| <prompt> (without the <>) | |
| ### Response: | |
| ``` |