《Reinforcement Learning from Human Feedback》繁體中文全譯本＋每章互動實驗 | Unofficial zh-TW community translation of the RLHF Book with interactive labs

[ CoStaff External Agent ] Get the data from twinkle hub mcp ADK Agent

Official repository for the Twinkle AI Late-Night Study Session. Features hands-on Jupyter notebooks, slides, and code for our book club on "Hands-On Large Language Models"

公開網站

The open source coding agent.

Write professional-grade skills for agents, validate them using LLMs, and maintain a lean context window.

AiyoPerps is a cryptocurrency perpetual futures trading application that supports leveraged trading on both decentralized exchanges and centralized exchanges. Include multi-tab market K-line charts…

Browser-native personal AI assistant. Zero infrastructure, the browser is the server.

LLaDA2.0 is the diffusion language model series developed by InclusionAI team, Ant Group.

Dataset of PNG images from synthetically generated table layouts with annotations in JSONL files

This is the Google ADK Agent Application - Gemini CLI Extension Project.

Advanced audio player component (audix) for Streamlit with waveform visualization and region selection

🌐 Twinkle AI "UnOfficial" Website

This repository implements a multi-agent red teaming framework designed to test the safety and robustness of large language models (LLMs). The system simulates a controlled adversarial environment …

AiyoDesk 以最低的硬體成本打造家用 AI 伺服器

A magical AI playground designed to bring the power of Large Language Models (LLMs) directly to your device.

Evaluation code for benchmarking VLMs in traditional chinese understanding

High-performance LLM evaluation framework with parallel API calls — up to 17× faster than sequential tools. Supports box, math, and logit-based evaluation.

PyMuPDF4LLM

從中文維基百科訓練 BPE Tokenizer

Python tool for converting files and office documents to Markdown.

The context API to search, scrape, and interact with the web at scale. 🔥

An open science effort to benchmark legal reasoning in foundation models

This repository provides scripts for evaluating NLP models on the LEXTREME benchmark, a set of diverse multilingual tasks in legal NLP

A Next-Generation Training Engine Built for Ultra-Large MoE Models

Official implementation of the paper "From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models"

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

【Hello CTF】专为CTF比赛封装的虚拟机，基于工具集封装多个版本和系统，更多选择，开箱即用。比赛愉快！