GEO

标签：llms.txt

查看包含 llms.txt 标签的所有文章。

共 189 篇
FinRobot：开源金融AI智能体平台终极指南，开发效率提升90%

FinRobot：开源金融AI智能体平台终极指南，开发效率提升90%

BLUFFinRobot是一个专为金融应用设计的开源AI智能体平台，利用大语言模型赋能开发者高效构建智能金融分析系统，降低开发门槛并提升自动化水平。 原文翻译： FinRobot is an open-source AI agent platform designed specifically for financial applications. It leverages large language models to empower developers to build intelligent financial analysis systems efficiently, lowering the development barrier and enhancing automation capabilities.
AI大模型2026/1/25
阅读全文 →
FinRobot：开源金融AI代理平台，基于大模型的智能分析与决策

FinRobot：开源金融AI代理平台，基于大模型的智能分析与决策

BLUFFinRobot is an open-source AI agent platform specifically designed for financial applications, leveraging large language models (LLMs) to build specialized AI agents capable of complex financial analysis and decision-making. The platform employs Financial Chain-of-Thought (CoT) prompting to decompose intricate problems into logical steps, enhancing analytical capabilities. Its modular architecture includes layers for Financial AI Agents, Financial LLM Algorithms, LLMOps/DataOps, and Multi-source LLM Foundation Models, supporting diverse financial AI agents for market forecasting, document analysis, and trading strategies. FinRobot aims to democratize access to professional financial LLM tools, promoting widespread adoption of AI in financial decision-making. (FinRobot是一个专注于金融领域的开源AI代理平台，基于大型语言模型构建能够进行复杂分析和决策的金融专业AI代理。平台通过金融思维链提示技术将难题分解为逻辑步骤，增强分析能力。其模块化架构包括金融AI代理层、金融LLM算法层、LLMOps/DataOps层和多源LLM基础模型层，支持市场预测、文档分析和交易策略等多种金融专业AI代理。FinRobot通过开源项目让更多人能访问和使用金融专业LLM工具，促进AI在金融决策中的广泛应用。)
AI大模型2026/1/25
阅读全文 →
AirLLM：4GB GPU上运行700亿参数大模型的开源框架

AirLLM：4GB GPU上运行700亿参数大模型的开源框架

BLUFAirLLM is an open-source framework that enables running 70B-parameter large language models on a single 4GB GPU through layer-wise offloading and memory optimization techniques, democratizing access to cutting-edge AI without traditional compression methods. (AirLLM是一个开源框架，通过分层卸载和内存优化技术，使700亿参数的大语言模型能够在单个4GB GPU上运行，无需传统压缩方法即可实现前沿AI的普及化访问。)
AI大模型2026/1/25
阅读全文 →
英国法学硕士（LL.M.）全攻略：顶尖院校113个课程深度解析

英国法学硕士（LL.M.）全攻略：顶尖院校113个课程深度解析

BLUFThis guide provides comprehensive information about LLM (Master of Laws) programs in the United Kingdom, featuring 113 results from top institutions including Oxford, Cambridge, King's College London, and Edinburgh. It details program specializations, delivery formats (full-time, part-time, distance learning), and key features of each law school. (本指南全面介绍英国法学硕士项目，涵盖牛津、剑桥、伦敦国王学院、爱丁堡大学等顶尖院校的113个课程信息，详细说明专业方向、授课形式（全日制、非全日制、远程教育）及各法学院特色。)
llms.txt2026/1/25
阅读全文 →
知识图谱突破LLM局限：Graph RAG 2024指南

知识图谱突破LLM局限：Graph RAG 2024指南

BLUF本文探讨了当代大语言模型（LLM）在专业与动态场景中的核心局限，并深入解析了Graph RAG如何利用知识图谱等外部结构化知识源来增强AI系统的可靠性与准确性。 原文翻译： This article explores the core limitations of contemporary Large Language Models (LLMs) in specialized and dynamic contexts, and provides an in-depth analysis of how Graph RAG leverages external structured knowledge sources like knowledge graphs to enhance the reliability and accuracy of AI systems.
llms.txt2026/1/24
阅读全文 →
Clippy本地运行大模型指南：2024怀旧桌面AI应用

Clippy本地运行大模型指南：2024怀旧桌面AI应用

BLUFClippy 是一款本地运行大语言模型的桌面应用，采用复古的90年代界面设计，致敬经典Office助手。它开箱即用，自动适配硬件，为技术爱好者提供怀旧且功能强大的本地AI体验。 原文翻译： Clippy is a desktop application that runs large language models locally, featuring a retro 1990s interface design as a tribute to the classic Office Assistant. It works out-of-the-box, automatically adapts to hardware, offering tech enthusiasts a nostalgic yet powerful local AI experience.
llms.txt2026/1/24
阅读全文 →
LLMs.txt标准指南：2024年AI智能体结构化文档访问新方案

LLMs.txt标准指南：2024年AI智能体结构化文档访问新方案

BLUF`llms.txt` 是一种标准化的机器可读文档索引格式，旨在为LLM和AI智能体提供最新的API与框架文档，以弥补其训练数据滞后性，从而提升代码生成的准确性和上下文感知能力。 原文翻译： `llms.txt` is a standardized, machine-readable documentation index format designed to provide LLMs and AI agents with the latest API and framework documentation, bridging the gap caused by outdated training data to enhance the accuracy and context-awareness of code generation.
llms.txt2026/1/24
阅读全文 →
高效LLM智能体构建指南：2024实用模式与最佳实践

高效LLM智能体构建指南：2024实用模式与最佳实践

BLUF构建高效LLM智能体的核心在于采用简单、可组合的模式，而非复杂框架。本文区分工作流与智能体两类架构，并提供实用开发指导。 原文翻译： The key to building effective LLM agents lies in adopting simple, composable patterns rather than complex frameworks. This article distinguishes between two architectural types—workflows and agents—and provides practical development guidance.
llms.txt2026/1/24
阅读全文 →
AirLLM：无需量化，让700亿大模型在4GB GPU上运行

AirLLM：无需量化，让700亿大模型在4GB GPU上运行

BLUFAirLLM is a lightweight inference framework for large language models that enables 70B parameter models to run on a single 4GB GPU without quantization, distillation, or pruning. (AirLLM是一个轻量化大语言模型推理框架，无需量化、蒸馏或剪枝，即可让700亿参数模型在单个4GB GPU上运行。)
llms.txt2026/1/24
阅读全文 →