263 个 · LLM 基础设施
基于 Jev API 的开放决策模型：通过前向传递给出带概率的类型化答案（yes/no、choice、score、multi），无需生成。基于 Qwen3.5-4B + LoRA，单卡 GPU。Open decisions model with Jev's API: typed answers (yes/no, choice, score, multi) with probabilities from forward passes, no generation. Qwen3.5-4B + LoRA, one GPU.
AI 原生 OS。模型运行在自有硬件上，节点点对点联邦无需代理，API 兼容 OpenAI。可启动，自带 Wayland 合成器，8GB 即可运行。Apache 2.0。An AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-compatible. Boots, has its own Wayland compositor, and runs on 8GB. Apache 2.0.
使用 GPT-3 辅助撰写基金申请书的实验Experiment to use GPT-3 to help write grant proposals.
对人类而言，语言是表达的工具；对 AI 而言，语言是推理的基底。For humans, a language is a tool for expression. For AIs, it's a substrate for reasoning.
AI 原生的结构化数据 wire 格式。在每个前沿模型上实现 100% 理解，比 JSON 减少 50-92% token，跨 17 种格式完成 43B+ 无损往返。Spec v3.4 Stable。The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.4 Stable.
精选 AI 模型及其 API 提供商列表，完全无需信用卡即可使用，欢迎贡献！Curated list of AI Models with their API Providers that you never ever require a Credit Card for. Feel free to Contribute!
面向 Claude Code 的学术研究工作流：包含 20 个 skill，覆盖因果推断（DiD、RDD、IV、合成控制、田野实验、设计分流、预注册）、论文阅读、文献综述、参考文献审计、复现包、LaTeX 与 TikZ，并附带带渲染时质量门禁的 Quarto reveal.js 幻灯片系统。Academic research workflow for Claude Code: 20 skills covering causal inference (DiD, RDD, IV, synthetic control, field experiments, design triage, preregistration), paper reading, lit review, bib auditing, replication packages, LaTeX and TikZ, plus a Quarto reveal.js slide system with render-time quality gates.
一个以证据为引领的六语种 LLM 实战手册：包含可迁移的核心、Codex 旗舰路线，以及 ChatGPT、Claude Code、Gemini、DeepSeek 和 Grok 的适配器。An evidence-led, six-language LLM playbook: the transferable core, the Codex flagship track, and adapters for ChatGPT, Claude Code, Gemini, DeepSeek, and Grok.
Run the native 284B-A13B DeepSeek-V4-Flash-0731 LLM locally on one laptop CPU: pure C, 8 GB RAM minimum, no GPU, best TPOT 0.892 s/token, resident OpenAI-compatible API with function tools. | 在笔记本单颗 CPU 上本地运行原生 284B-A13B DeepSeek-V4-Flash-0731 大模型：纯 C，最低 8 GB 内存，无需 GPU，最优 TPOT 0.892 秒/token，支持模型常驻的 OpenAI 兼容接口与函数工具。
🦙 使用 Ollama CLI 配置 GitHub Actions。🦙 Set up GitHub Actions with Ollama CLI.
为赫尔辛基大学师生打造的 LLM 聊天工具，用于教育与研究。LLM chat built for University of Helsinki staff and students, for education and research.
将 Zotero 阅读器标注评论渲染为 Markdown 和 LaTeX 格式，同时保留存储的原始文本。Render Zotero reader annotation comments as Markdown and LaTex while preserving stored text.
本地 AI 秘书、技术支持与销售一体化方案，基于 XTTS v2 语音克隆、Vosk/Whisper 实时语音识别与 vLLM + Qwen/Llama 等离线 LLM。配备 Vue 3 完整管理面板、Telegram Bot、网站挂件及 fine-tuning pipeline。支持自托管、数据隐私、短信与电话呼叫。📞 Локальный AI-секретарь, тех. поддержка и менеджер по продажам с клонированием голоса XTTS v2, real-time распознаванием речи (Vosk/Whisper) и offline LLM (vLLM + Qwen/Llama и тп). Полноценная админ-панель (Vue 3), Telegram-бот, виджет для сайта, fine-tuning pipeline. Self-hosted, приватность данных, СМС и телефонные звонки .
运行 Ollama 本地 LLM 服务的 Docker 镜像。默认安全，所有 API 请求需 Bearer token（首次启动时自动生成）。OpenAI 兼容 API。支持首次启动模型预拉取、NVIDIA GPU (CUDA) 加速和持久化模型存储。多架构：amd64、arm64。Docker image to run an Ollama local LLM server. Secure by default, all API requests require a Bearer token (auto-generated on first start). OpenAI-compatible API. Supports first-start model pre-pull, NVIDIA GPU (CUDA) acceleration, and persistent model storage. Multi-arch: amd64, arm64.
通用学术写作 Agent Skill：论文润色、中英互译、学位论文与基金申请、审稿回复与投稿材料，适用于各学科；不改数据、不编文献、不夸大结论。支持 Claude Code、Codex、Cursor、Grok Build、OpenCode，复制提示词即可安装。
并行运行 Claude Code、Codex 与 Gemini，并支持彼此交接任务。面向 AI CLI 的便携 Windows 终端。Run Claude Code, Codex and Gemini side by side — and let them hand work to each other. Portable Windows terminal for AI CLIs.
Gebo.ai —— 开源、企业级、与 AI 供应商无关的平台Gebo.ai The open source Enterprise AI vendor agnostic platform
STEPQuant: Delta 规则循环状态量化中错误在何时何处重要STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
💻 在 macOS 上借助 Metal GPU 实现 Qwen3 Transformer 模型，获得加速且高效的性能，并支持关键架构特性💻 Implement Qwen3 transformer model on macOS using Metal GPU for accelerated, efficient performance with support for key architecture features.
本仓库包含用于执行不同任务的 Gen AI 项目temThis repository contains Gen AI projects that performs different tasks
以孟加拉语优先、面向方言的 LLM 研究。开源孟加拉语 tokenizer，性能优于 Sarvam、AI4Bharat 和 GPT-4o（fertility 1.52，几乎零破损 conjuncts）。非商用，保护孟加拉语及其方言。Bengali-first, dialect-aware LLM research. Open-source Bengali tokenizer that outperforms Sarvam, AI4Bharat, and GPT-4o (fertility 1.52, near-zero broken conjuncts). Non-commercial, preserving Bengali and its dialects.
🚀 通过 70 个生成式 AI 实战项目转型技能，从入门到生产级架构师，涵盖真实场景应用。🚀 Transform your skills with 70 hands-on projects in Generative AI, guiding you from beginner to production-ready architect with real-world applications.
大语言模型元数据的开放注册表——以单一机器可读的 models.json 提供身份、作者、模态、上下文/输出限制、能力与生命周期日期，并通过 JSON Schema 校验。CC BY 4.0Open registry of large-language-model metadata — identity, authorship, modalities, context/output limits, capabilities & lifecycle dates as one machine-readable models.json validated by JSON Schema. CC BY 4.0.
🛠️ 通过 Local-LLM（一款基于 BERT 模型的轻量级 Python 库）在安全环境中实现离线 NLP 工作流，确保可复现性与可靠性。🛠️ Enable offline NLP workflows with Local-LLM, a lightweight Python library for secure environments using the BERT model, ensuring reproducibility and reliability.
开放兼容性测试网络：该库 API 是否能在你的版本、操作系统和运行时上真正运行？提供真实构建证据、已验证样本以及每个结果对应的运行环境。An open compatibility testing network: does this library API actually run on your version, OS and runtime? Real build evidence, verified samples, and the environment each result came from.
Tox21 多终点毒性预测：可复现的研究与推理制品（冻结模型、FastAPI 服务、已审计的安全机制）Tox21 multi-endpoint toxicity prediction: a reproducible research and inference artifact (frozen model, FastAPI service, audited security)
THIS PAPER IS FOR ENTERTAINMENT PURPOSES ONLY.この小説はフィクションであり、実在する団体または個人とは関係ありません。
基于 TurboQuant 优化 FAISS 兼容的向量量化，实现快速、精准的向量检索。Optimize FAISS-compatible vector quantization for fast, accurate vector search with TurboQuant
轻松优化面向 AI 系统的 prompt，借助直观工具与特性提升性能🚀 Optimize your prompts for AI systems easily and boost performance with intuitive tools and features designed for better results.
《大模型推理原理与优化》：面向系统/架构/后端研发工程师的模型原理入门课，目标是通俗易懂的解释推理过程，理解原理有助于系统开发/维护工作
DP-ES 官方实现：面向 Prompt 优化的差分隐私进化策略（EMNLP 2026）。Official implementation of DP-ES: Differentially Private Evolution Strategies for Prompt Optimization (EMNLP 2026)
一个可复用的 Codex Skill，用于证据对齐、AI 与人工审稿人就绪的学术写作。A reusable Codex skill for evidence-aligned, AI- and human-reviewer-ready academic writing.
面向生产环境的、有内存约束的跨模型 KV-cache 传输，具备受保护的回退机制与可复现研究工具链。Production-oriented, memory-bounded cross-model KV-cache transfer with guarded fallback and reproducible research tooling.
混合神经符号 AI：Llama 3.2 1B + 精确数学 + 经验证事实，807 MB 即时 CPU 原生回答，无需 GPU。封装 .aef 分发。Hybrid neuro-symbolic AI: Llama 3.2 1B + exact math + verified facts — instant CPU-native answers in 807 MB, no GPU. Sealed .aef distribution