Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Fine-tuning & Reinforcement Learning for LLMs. π¦₯ Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
An autonomous agent that conducts deep research on any data using any LLM providers.
Prefect is a workflow orchestration framework for building resilient data pipelines in Python.
verl: Volcano Engine Reinforcement Learning for LLMs
Minimal reproduction of DeepSeek R1-Zero
A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.
Tools for merging pretrained large language models.
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isβ¦
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
Entropy Based Sampling and Parallel CoT Decoding
idiap / coqui-ai-TTS
Forked from coqui-ai/TTSπΈπ¬ - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Versatile audio super resolution (any -> 48kHz) with AudioSR.
AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
Work with Apple MacOS Notes.app from the command line. Also includes python interface for scripting Notes.app from your own python code.
Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to potentially execute offline remote code execution without runninβ¦
Mozer / YuE-extend
Forked from alisson-anjos/YuE-exllamav2-UIYuE with mp3 extend, exllama and GUI
[AAAI 2026] Code of the paper "GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization"
A Python script that converts text/gemini into HTML.