仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

Verifiers for LLM Reinforcement Learning

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Reproduce R1 Zero on Logic Puzzle

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

OCR, layout analysis, reading order, table recognition in 90+ languages

This repo includes Claude prompt curation to use Claude better.

用文本编辑器剪视频

This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and there are three …

Postman collection for Binance Public API, including spot, margin, futures, etc.

Xiaomi Home Integration for Home Assistant

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

Train a 1B LLM with 1T tokens from scratch by personal

A simple, easy-to-hack GraphRAG implementation

Port of Funasr's Sense-voice model in C/C++

First-principle implementations of groundbreaking AI algorithms using a wide range of deep learning frameworks, accompanied by supporting research papers.

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

A simple screen parsing tool towards pure vision based GUI agent

[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

小爱音箱mini定制固件 Let the Xiao Ai Speaker Mini free

📺IPTV电视直播源更新项目『✨秒播级体验🚀』：支持IPv4/IPv6；支持自定义频道；支持本地源、组播源、酒店源、订阅源、关键字搜索；每天自动更新两次，结果可用于TVBox等播放软件；支持工作流、Docker(amd64/arm64/arm v7)、命令行、GUI运行方式 | IPTV live TV source update project

Network Analysis in Python

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

A modular graph-based Retrieval-Augmented Generation (RAG) system

Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction

NanoGPT (124M) in 3 minutes

Build android apps without any java, entirely in C and Make

Variational Autoencoder and Conditional Variational Autoencoder on MNIST in PyTorch

智能视频多语言AI配音/翻译工具 - Linly-Dubbing — “AI赋能，语言无界”