jnewman

Joshua Newman's starred repositories

grok-1

Grok open release

Language:PythonApache-2.048987 553 197

autogen

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

Language:Jupyter NotebookCC-BY-4.026998 355 1321

git-lfs

Git extension for versioning large files

Language:GoNOASSERTION12592 487 3023

dspy

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

Language:PythonMIT12506 116 504

rye

a Hassle-Free Python Experience

Language:RustMIT11860 55 507

OpenLLM

Run any open-source LLMs, such as Llama 2, Mistral, as OpenAI compatible API endpoint in the cloud.

Language:PythonApache-2.09088 53 251

minbpe

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

Language:PythonMIT8511 80 33

gitoxide

An idiomatic, lean, fast & safe pure Rust implementation of Git

Language:RustApache-2.08177 51 458

asyncpg

A fast PostgreSQL Database Client Library for Python/asyncio.

Language:PythonApache-2.06687 121 767

mamba

The Fast Cross-Platform Package Manager

Language:C++BSD-3-Clause6420 48 1647

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

Language:PythonApache-2.05287 28 532

agents

An Open-source Framework for Autonomous Language Agents

Language:PythonApache-2.04619 59 68

simclr

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

Language:Jupyter NotebookApache-2.03972 47 196

awesome-mlops

:sunglasses: A curated list of awesome MLOps tools

Language:Python3673 81 7

torchscale

Foundation Architecture for (M)LLMs

Language:PythonMIT2951 46 75

phoenix

AI Observability & Evaluation

Language:Jupyter NotebookNOASSERTION2860 27 1618

modeldb

Open Source ML Model Versioning, Metadata, and Experiment Management

Language:JavaApache-2.01682 67 141

ort

A suite of tools to automate software compliance checks.

Language:KotlinApache-2.01499 41 1228

grpclib

Pure-Python gRPC implementation for asyncio

Language:PythonBSD-3-Clause916 29 156

Texygen

A text generation benchmarking platform

Language:PythonMIT860 47 49

Adala

Adala: Autonomous DAta (Labeling) Agent framework

Language:PythonApache-2.0820 19 12

docker-squash

Docker image squashing tool

Language:PythonMIT794 22 154

test-reporter

Displays test results from popular testing frameworks directly in GitHub

Language:TypeScriptMIT743 11 138

LLM-Pruner

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support LLaMA, Llama-2, BLOOM, Vicuna, Baichuan, etc.

Language:PythonApache-2.0701 13 58

gretel-synthetics

Synthetic data generators for structured and unstructured text, featuring differentially private learning.

Language:PythonNOASSERTION550 25 46

parsel

Code for Parsel 🐍 - generate complex programs with language models

Language:Python381 10 6

rudolfs

A high-performance, caching Git LFS server with an AWS S3 and local storage back-end.

Language:RustMIT350 5 32

croissant

Croissant is a high-level format for machine learning datasets that brings together four rich layers.

Language:PythonApache-2.0306 21 190

github-actions-dhall

Typecheck, template and modularize your Github Action definitions with Dhall

Language:DhallMIT109 4 16

idea-demo-devcontainers

initial

Language:Java2600