An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems

SGLang is a high-performance serving framework for large language models and multimodal models.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Library for fast text representation and classification.

Official Code for "Coser: Coordinating LLM-Based Persona Simulation of Established Roles"

PyTorch入门教程，在线阅读地址：https://datawhalechina.github.io/thorough-pytorch/

Data manipulation and transformation for audio signal processing, powered by PyTorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

GLM-4-Voice | 端到端中英语音对话模型

RoFormer V1 & V2 pytorch

Rotary Transformer

Self-Supervised Speech Pre-training and Representation Learning Toolkit

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

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

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

A high-throughput and memory-efficient inference and serving engine for LLMs

Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

slime is an LLM post-training framework for RL Scaling.

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Robust Speech Recognition via Large-Scale Weak Supervision

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

ClickBench: a Benchmark For Analytical Databases

The agent engineering platform.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

A Tool to Visualize Claude Code's LLM Interactions