This project was made for studying LLMs and how they're implemented without any abstraction libraries such as those made by Hugging Face. The goal is to implement a basic GPT-2-esque LLM with libraries consisting of the standard library, PyTorch and Pandas. The idea of using 4chan as the basis for the training dataset came from this Kitboga-lookalike Yannic Kilcher's YouTube video.
-
Notifications
You must be signed in to change notification settings - Fork 0
ymcx/llmfs
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published