sutyum

LLMs-from-scratch

Implementing a ChatGPT-like LLM from scratch, step by step

c-app-demo

A simple demo to show how to structure c apps

cgrad

cu.cu

cuda-kuma kernels

dbos-transact-py

Ultra-Lightweight Durable Execution in Python

distributed-training-guide

Best practices & guides on how to write distributed pytorch training code

docs

LLaMA-Omni

Low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct.

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

pytudes

Python programs, usually short, of considerable difficulty, to perfect particular skills.

webrtc-ai-voice-chat

A WebRTC server that allows you to interact with an LLM using your speech and responds back with generated audio.

zeta

Build high-performance AI models with modular building blocks

print-c

fmt like, minimal single header c library

torch-models

Learning by implementing core papers

dspy

DSPy: The framework for programming with foundation models

gpt2

kickstart.nvim

A launch point for your personal nvim configuration

learn-kas

LearnToClarify

RL on verifiable rewards for LLM to learn to ask clarifying questions

libpeer

WebRTC Library for IoT/Embedded Device using C

llm-verify

mini-omni

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

minimal_nn

mojo

The Mojo Programming Language

OpenStrawberry

An open source replication of the stawberry method that leverages Monte Carlo Search with PPO and or DPO

playing-with-ray

qt5_comprehensive_example

RAGatouille

tmux-kickstarter

A semi-opinionated tmux config

verifiers

Verifiers for LLM Reinforcement Learning