🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Robust Speech Recognition via Large-Scale Weak Supervision

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

No fortress, purely open ground. OpenManus is Coming.

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

C++那些事

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

🔊 Text-Prompted Generative Audio Model

A generative speech model for daily dialogue.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Open-Sora: Democratizing Efficient Video Production for All

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

Fully open reproduction of DeepSeek-R1

A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

verl: Volcano Engine Reinforcement Learning for LLMs

✨✨Latest Advances on Multimodal Large Language Models

Train transformer language models with reinforcement learning.

<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

A multi-voice TTS system trained with an emphasis on quality

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …

FlashMLA: Efficient Multi-head Latent Attention Kernels

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

The official GitHub page for the survey paper "A Survey of Large Language Models".

Foundational Models for State-of-the-Art Speech and Text Translation