vincentweisser

Liger-Kernel

Efficient Triton Kernels for LLM Training

claude-dev

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, and more with your permission every step of the way.

ADAS

Automated Design of Agentic Systems

prime-intellect-test

aphrodite-engine

PygmalionAI's large-scale inference engine

agents

Trade autonomously on Polymarket using AI Agents

AI-Scientist

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

quiet-star

Code for Quiet-STaR

augmentoolkit

Convert Compute And Books Into Instruct-Tuning Datasets (or classifiers)!

teeML

Galadriel TEE oracle configuration and verification code

globot

Globot is an agent that controls your browser using playwright and GPT-4V.

awesome-golem

A community-curated list of awesome projects and resources related to the Golem peer-to-peer computational resources marketplace.

leabra

Go implementation of Leabra algorithm for biologically-based models of cognition, based on emergent framework (with Python interface)

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

miner-release

Stable Diffusion and LLM miner for Heurist

system-2-research

System 2 Reasoning Link Collection

AGI-Papers

Papers and Book to look at when starting AGI 📚

STaR

Code for STaR: Bootstrapping Reasoning With Reasoning (NeurIPS 2022)

ToRA

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

llama-agentic-system

Agentic components of the Llama Stack APIs

open-webui

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

exo

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

shap-e

Generate 3D objects conditioned on text or images

Obsidian

Maybe the new state of the art vision model? we'll see 🤷‍♂️

Open-Reasoning-Tasks

A comprehensive repository of reasoning tasks for LLMs (and beyond)

open_lm

A repository for research on medium sized language models.

algorithmic-efficiency

MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvements in both training algorithms and models.

OpenDiloco

OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training

mistral-finetune

mistral-inference

Official inference library for Mistral models