ryOS, made with Cursor

这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。

「妙幕」是一款跨平台客户端工具，可以批量为视频或者音频生成字幕文件，并支持对字幕进行翻译，支持百度、火山、openai、ollama、deepseek 等多家翻译

Awesome Reasoning LLM Tutorial/Survey/Guide

The simplest, fastest repository for training/finetuning medium-sized GPTs.

🤗 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.

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

LLM inference in C/C++

Questions that I ask myself at the end of each year and each decade.

Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个

Compact and Efficient RISC-V RV32I[MAFC] emulator

Official inference framework for 1-bit LLMs

AI app store powered by 24/7 desktop history. open source | 100% local | dev friendly | 24/7 screen, mic recording

Generative AI extensions for onnxruntime

Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-t…

MemoAI Video to translated text, subtitles and notes made easy.

⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks

Attention is all you need implementation

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

A very simple command line tool to convert heic files to jpg

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

Simple Online Realtime Tracking with a Deep Association Metric

Mamba SSM architecture

llama3 implementation one matrix multiplication at a time

Copy book is a collection of texts that are commonly used around the web.

Traditional Mandarin LLMs for Taiwan

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.

AIOS: AI Agent Operating System

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Few Shot Object Detection Papers