PygmalionAI's large-scale inference engine

Trade autonomously on Polymarket using AI Agents

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

Code for Quiet-STaR

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

Galadriel TEE oracle configuration and verification code

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

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

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

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

Stable Diffusion and LLM miner for Heurist

System 2 Reasoning Link Collection

Papers and Book to look at when starting AGI 📚

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

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

Agentic components of the Llama Stack APIs

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

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

Generate 3D objects conditioned on text or images

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

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

A repository for research on medium sized language models.

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

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

Official inference library for Mistral models

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

AGiXT is a dynamic AI Agent Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features…

A Gradio web UI for Large Language Models.

"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts" (NeurIPS 2020), original PyTorch implementation