Triton nanoGPT With Custom Cross Entropy Loss Kernel

Triton nanoGPT With Custom Cross Entropy Loss Kernel

Lightweight implementation of newly introduced “Differential Transformer”:

nanoGPT with Sigmoid Self-Attention

PyTorch implementation of “Self-Compressing Neural Networks” paper.

Port of Karpathy’s Micrograd in Pure C

BrainGPT Demo 🧠🤖💥

Training GPT-2 Locally (on CPU) in Pure C With Karpathy's llm.c

MLX RAG with GGUF Models

min-patchnizer update!!

LLM “Patchnization”

GPT (nanoGPT) from a beginner’s perspective (Part 2 Final)

GPT (nanoGPT) from a beginner's perspective (Part 1)