https://github.com/en10/tinygpt

https://github.com/en10/tinygpt

Last synced: over 1 year ago
JSON representation

• Host: GitHub
• URL: https://github.com/en10/tinygpt
• Owner: EN10
• License: mit
• Created: 2023-12-29T13:07:23.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2023-12-29T20:06:44.000Z (over 2 years ago)
• Last Synced: 2025-02-01T09:43:54.089Z (over 1 year ago)
• Language: Jupyter Notebook
• Size: 10.7 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# TinyGPT

Train and run a [nanoGPT](https://github.com/karpathy/ng-video-lecture/blob/master/gpt.py) model from scratch on the [TinyStories](https://huggingface.co/datasets/roneneldan/TinyStories) dataset.

* ## [TinyGPT Colab](https://github.com/EN10/TinyGPT/blob/main/TinyGPT.ipynb)

### Based on:

* [Original Karpathy Colab](https://colab.research.google.com/drive/1JMLa53HDuA-i7ZBmqV7ZnA3c_fvtXnx-?usp=sharing#scrollTo=2c5V0FvqseE0)

* [Karpathy Video](https://www.youtube.com/watch?v=kCc8FmEb1nY)