Highlights
- Pro
Stars
Benchmark suite for models of musical expectation
PyTorch Code for Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms
Code for NeurIPS 2024 paper - The GAN is dead; long live the GAN! A Modern Baseline GAN - by Huang et al.
A TTS that fits in your CPU (and pocket)
AI agents running research on single-GPU nanochat training automatically
FlashInfer: Kernel Library for LLM Serving
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
why use many token when few token do trick. Skill + local proxy for coding agents: shorter answers, smaller tool output, every original recoverable.
MNE: Magnetoencephalography (MEG) and Electroencephalography (EEG) in Python
a python3 version of matlab mTRF-Toolbox by Lalor Lab https://mtrfpy.readthedocs.io/
GPT-2 transformer for controllable, multitrack symbolic music generation
Scripting Music2Latent to TorchScript for streamable continuous inference in MaxMSP/PureData
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Fast and memory-efficient exact attention
Universal Notation for Tensor Operations in Python
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Minimalistic large language model 3D-parallelism training
HeartMuLa Official Repo: The Most Powerful Open-Source Music Generation Model of 2026
C++ Library for tokenizing MIDI files, designed to be compatible with the MIDITok python library
A python package for handling modern staff notation of music
[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation
Unified Implementations of Offline Reinforcement Learning Algorithms
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
An interface library for RL post training with environments.
Encode and decode audio samples to/from continuous and discrete compressed representations!
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
Unified automatic quality assessment for speech, music, and sound.