mlmabie

build-your-own-x

Master programming by recreating your favorite technologies from scratch.

ComfyUI

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

so-vits-svc

SoftVC VITS Singing Voice Conversion

delta

A syntax-highlighting pager for git, diff, grep, and blame output

LLMs-from-scratch

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

mlx

MLX: An array framework for Apple silicon

ml-engineering

Machine Learning Engineering Open Book

cv

Print-friendly, minimalist CV page

minbpe

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

outlines

Structured Text Generation

rags

Build ChatGPT over your data, all with natural language

GPU-Puzzles

Solve puzzles. Learn CUDA.

alphageometry

AlphaCodium

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

ColBERT

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

Tensor-Puzzles

Solve puzzles. Improve your pytorch.

weak-to-strong

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.

LLM-Finetuning

LLM Finetuning with peft

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

airoboros

Customizable implementation of the self-instruct paper.

vec2text

utilities for decoding deep representations (like sentence embeddings) back to text

gritlm

Generative Representational Instruction Tuning

claude-app-generator-demo

This app was generated by Claude 3 Opus in one go without help

humane.watch

Humane ai pin on the Apple watch

AutoStory

llm-mistral

LLM plugin providing access to Mistral models using the Mistral API

calibur

Conversion between different conventions of camera matrices and transform matrices.

massive-activations

Code accompanying the paper "Massive Activations in Large Language Models"

DipoleAttention