NanoGPT (124M) in 3 minutes

The best ChatGPT that $100 can buy.

Building Tiny Recursive Models from Scratch

[ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2

Implementation of the paper from Liquid AI

procedural reasoning datasets

A PyTorch implementation of the Hyena-Y model, a convolution-based multi-hybrid architecture optimized for edge devices.

Storing long contexts in tiny caches with self-study

Model interpretability and understanding for PyTorch

A PyTorch-based Speech Toolkit

codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)

AlphaGo Moment for Model Architecture Discovery.

Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Hierarchical Reasoning Model Official Release

Official repository for Mi:dm 2.0, the large language model developed by KT.

A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).

cellular automata simulation using difflogic neural network and synthesize a digital logic circuit using difflogic.

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models

Official repository for EXAONE 4.0 built by LG AI Research

Simple & Scalable Pretraining for Neural Architecture Research

A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour

Kimi K2 is the large language model series developed by Moonshot AI team

nannyml: post-deployment data science in python

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Muon is an optimizer for hidden layers in neural networks

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Memory for AI Agents; Announcing OpenMemory MCP - local and secure memory management.