jeremyjordan

open-interpreter

A natural language interface for computers

whisper.cpp

Port of OpenAI's Whisper model in C/C++

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

dspy

DSPy: The framework for programming—not prompting—foundation models

MemGPT

Create LLM agents with long-term memory and custom tools 📚🦙

LLMsPracticalGuide

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

FastUI

Build better UIs faster.

outlines

Structured Text Generation

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

composer

Supercharge Your Model Training

gateway

A Blazing Fast AI Gateway. Route to 200+ LLMs with 1 fast & friendly API.

morphic

An AI-powered search engine with a generative UI

torchtune

A Native-PyTorch Library for LLM Fine-tuning

Tensor-Puzzles

Solve puzzles. Improve your pytorch.

ColBERT

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

kopf

A Python framework to write Kubernetes operators in just a few lines of code

schedule_free

Schedule-Free Optimization in PyTorch

openllmetry

Open-source observability for your LLM application, based on OpenTelemetry

resemble-enhance

AI powered speech denoising and enhancement

axlearn

An Extensible Deep Learning Library

rcg

PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

mirascope

An intuitive approach to building with LLMs

levanter

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

testpilot

Test generation using large language models

audioflare

An all-in-one AI audio playground using Cloudflare AI Workers to transcribe, analyze, summarize, and translate any audio file.

brainworkshop

Continued development of the popular brainworkshop game

diarizers

cookbook

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

lakehouse-engine

The Lakehouse Engine is a configuration driven Spark framework, written in Python, serving as a scalable and distributed engine for several lakehouse algorithms, data flows and utilities for Data Products.

slides