Starred repositories
Universal LaTeX document skill for Claude Code: 27 templates, 22 scripts, 22 reference guides. Made with Claude Code on ✦ HappyCapy AI ✦ platform
Model Context Protocol(MCP) 编程极速入门
The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.
哔哩下载姬(跨平台版)downkyi，哔哩哔哩网站视频下载工具，支持批量下载，支持8K、HDR、杜比视界，提供工具箱（音视频提取、去水印等）。
哔哩下载姬downkyi，哔哩哔哩网站视频下载工具，支持批量下载，支持8K、HDR、杜比视界，提供工具箱（音视频提取、去水印等）。
[ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models
Text-audio foundation model from Boson AI
[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers
An open-access benchmark and toolbox for electricity price forecasting
Official Documentation for the Binance Spot APIs and Streams
Simple connector to Binance Public API
All Cursor AI's official download links for both the latest and older versions, making it easy for you to update, downgrade, and choose any version. 🚀
🚀 「大模型」1小时从0训练67M参数的视觉多模态VLM！🌏 Train a 67M-parameter VLM from scratch in just 1 hours!
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!
Official implementation for "TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables" (NeurIPS 2024)
Fast bare-bones BPE for modern tokenizer training
Pretraining and inference code for a large-scale depth-recurrent language model
[ICLR2026] This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incen…
ProBench: Benchmarking Large Language Models in Competitive Programming
Fast and memory-efficient exact attention
An Open Large Reasoning Model for Real-World Solutions
QQNT 插件加载器：LiteLoaderQQNT —— 轻量 · 简洁 · 开源 · 福瑞
A book for Learning the Foundations of LLMs
Fully open reproduction of DeepSeek-R1