Skip to content

Simple and curious tiny GPT model trained on Tiny Shakespeare Dataset.

License

Notifications You must be signed in to change notification settings

diegowarp/Tiny-GPT-from-Scratch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Tiny GPT from Scratch

Simple and curious tiny GPT model trained on Tiny Shakespeare Dataset.

To develop this Tiny GPT model, I followed an incredible YouTube tutorial by Andrej Karpathy. I also utilized important articles to apply the concepts, such as "Attention is All You Need" and "Language Models are Few-Shot Learners."

For training, the TinyShakespeare dataset (~1115394 characters) was used, with 5000 epochs of training.

The final model had 209,729 trainable parameters and is capable of forming sentences, albeit somewhat disconnected, readable, and well-punctuated.

About

Simple and curious tiny GPT model trained on Tiny Shakespeare Dataset.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published