VatsaDev

grok-1

Grok open release

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

OpenDevin

🐚 OpenDevin: Code Less, Make More

aseprite

Animated sprite editor & pixel art tool (Windows, macOS, Linux)

llm.c

LLM training in simple, raw C/CUDA

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

01

The open-source language model computer

moondream

tiny vision language model

alphageometry

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

cramming

Cramming the training of a (BERT-type) language model into limited compute.

yet-another-applied-llm-benchmark

A benchmark to evaluate language models on questions I've previously asked them to solve.

quiet-star

Code for Quiet-STaR

galactic

data cleaning and curation for unstructured text

TPU-Alignment

Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free

mamba.c

Inference of Mamba models in pure C

xVal

Repository for code used in the xVal paper

gptcore

Fast modular code to create and train cutting edge LLMs

othello_mamba

Evaluating the Mamba architecture on the Othello game

quartic-transformer

Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)

FaceRWKV

Course Project for COMP4471 on RWKV

Lilith

Using the lilith optimizer on nanogpt

tiny-asic-4bit-matrix-mul

Tiny matrix multiplication ASIC with 4-bit math

AIMO-Competition

JsLabs

make and store pages in the url, using url vars

TransformerMath

Can transformers learn math, like patterns?

2024-Swerve-concept

Describing Swerve functionality, mockup math

opencv-images

NCPT-Lilith

A retrain of the old nanogpt, but with the lilith optimizer

todo-fbla

the todo fbla project