Top Repositories on Github with TechGarden

Automate Creation of YouTube Shorts using MoviePy.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

lightweight, standalone C++ inference engine for Google's Gemma models.

16-bit CPU for Excel, and related files

The official PyTorch implementation of Google's Gemma models

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

It's sudo, for Windows

Building the best system design resource in the internet

MiniCPM-2B: An end-side LLM outperforms Llama2-13B.