jaebeompark

PruneMe

Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models

DistillKit

An Open Source Toolkit For LLM Distillation

sglang

SGLang is yet another fast serving framework for large language models and vision language models.

MovieDreamer

awesome-production-llm

A curated list of awesome open-source libraries for production LLM

MINT-1T

MINT-1T: A one trillion token multimodal interleaved dataset.

Shapeshift

Transform JSON objects using vector embeddings

MobileLLM

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

txtai

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

korvus

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

R2R-Application

react + next.js dashboard for R2R: production-ready RAG engine with a sh*t ton of features.

xLAM

persona-hub

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

Algorithm-Of-Thoughts

My implementation of "Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models"

tau-bench

Code and Data for Tau-Bench

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

llama3.1-rag-bot

Llama3.1 RAG system

R2R

The Supabase for RAG - R2R lets you build, scale, and manage user-facing Retrieval-Augmented Generation applications in production.

speechbrain

A PyTorch-based Speech Toolkit

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

rocksdb

A library that provides an embeddable, persistent key-value store for fast storage.

baml

BAML is a templating language to write typed LLM functions. Check out the promptfiddle.com playground

LLMs-from-scratch

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

MoA

Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models

Qwen-Agent

Agent framework and applications built upon Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

quickchart

Chart image and QR code web API

LLM-PlayLab

This playlab encompasses a multitude of projects crafted through the utilization of Large Language Models, showcasing the versatility and impact of these models across various applications.

Llama3-on-Mobile

This repository is an implementation of quantizing and converting the Llama3-8B-Instruct model weights and deploying it on Android for on-device inference.

lancedb

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

JamAIBase

Firebase for AI Agents: Open-source backend platform that puts powerful generative models at the core of your database. With managed memory and RAG capabilities, developers can easily build AI agents, enhance their apps with generative tables, and create magical UI experiences.