Official implementation of MAIA, A Multimodal Automated Interpretability Agent

The official Meta Llama 3 GitHub site

📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies

Composio equips agents with well-crafted tools empowering them to tackle complex tasks

Distributed LLM inference for mobile, desktop and server.

PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and effici…

Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks. This tool combines the capa…

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…

An opinionated, Agentic Engineering toolbox powered by LLM Agents to solve problems autonomously.

Official Implementation of "Multi-Head RAG: Solving Multi-Aspect Problems with LLMs"

This is a comprehensive training/testing environment using the Transformer model for solving Math Word Problems. Features easy configuration for novice users.

Problem solving by engaging multiple AI agents in conversation with each other and the user.

Official implementation for "OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities" (keep updating)

Agentless🐱: an agentless approach to automatically solve software development problems

Seq2Tree model for Solving Math Word Problems

All about how to make machines learn by themselves and break the limits of imagination.

Code for Graph-to-Tree Learning for Solving Math Word Problems (ACL 2020)

Combining Symbolic and Function Evaluation Expressions In Neural Programs

Official implementation of paper "Cumulative Reasoning With Large Language Models" (https://arxiv.org/abs/2308.04371)

A math application/chatbot to answer a user's arithmetic or reasoning based questions. Utilizes LangChain agents and tools. Frontend with Chainlit.

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Generative AI for Math: MathPile

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

Official Pytorch Implementation for MathGLM

Tools for using computer algebra systems to solve math problems step-by-step with reinforcement learning

Data and code for the paper "A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level" by Drori et al., 2022.

Reference models and tools for Cloud TPUs.

Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"