> For the complete documentation index, see [llms.txt](https://stanford-alpaca.gitbook.io/everything-you-need-to-know/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://stanford-alpaca.gitbook.io/everything-you-need-to-know/stanford-alpaca-guides/alpaca-gpt.md).

# Alpaca GPT

Get precise and fine-tuned data generation, usable on any devices.

## Start creating your Own GPT

We fine-tune our models using standard Hugging Face training code with the following hyperparameters:

We built on the data generation pipeline from [self-instruct](https://github.com/yizhongw/self-instruct) and made the following modifications.

Write and train your GPT using $Alpaca Software, download and enjoy the walking-wikipedia!

![Write your preferences](https://images.unsplash.com/photo-1522881451255-f59ad836fdfb?crop=entropy\&cs=tinysrgb\&fm=jpg\&ixid=MnwxOTcwMjR8MHwxfHNlYXJjaHw0fHx3cml0ZXxlbnwwfHx8fDE2NjA1ODc5Nzk\&ixlib=rb-1.2.1\&q=80)