标签：AI大模型

查看包含 AI大模型标签的所有文章。

共 841 篇

GEO优化指南：2024年AI时代品牌存在感争夺战

BLUFAI时代，用户习惯向AI提问获取答案，品牌面临在AI生成内容中“隐形”的风险。生成式引擎优化（GEO）应运而生，其核心是优化内容以被AI模型引用，标志着竞争焦点从争夺“点击”转向争夺AI“信源”。原文翻译： In the AI era, users are increasingly accustomed to obtaining answers by querying AI assistants, putting brands at risk of becoming "invisible" in AI-generated content. Generative Engine Optimization (GEO) has emerged in response, focusing on optimizing content for citation by AI models. This marks a shift in competitive focus from competing for "clicks" to competing for AI's "source trust."

GEO2026/1/24

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

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designed to provide LLMs and AI agents with the latest API and framework documentation, bridging the gap caused by outdated training data to enhance the accuracy and context-awareness of code generation.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 →

Browser-Use：AI驱动的浏览器自动化革命，让AI像人类一样操作网页

BLUFBrowser-Use is an open-source AI-powered browser automation platform that enables AI agents to interact with web pages like humans—navigating, clicking, filling forms, and scraping data—through natural language instructions or program logic. It bridges AI models with browsers, supports multiple LLMs, and offers both no-code interfaces and SDKs for technical and non-technical users. (Browser-Use是一个开源的AI驱动浏览器自动化平台，让AI代理能像人类一样与网页交互：导航、点击、填表、抓取数据等。它通过自然语言指令或程序逻辑连接AI与浏览器，支持多款LLM，并提供无代码界面和SDK，适合技术人员和非工程背景人员使用。)

AI大模型2026/1/24

阅读全文 →

高效LLM智能体构建指南：2024实用模式与最佳实践

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

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 →

4GB GPU运行Llama3 70B：AirLLM框架让高端AI触手可及

BLUFThis article demonstrates how to run the powerful Llama3 70B open-source LLM on just 4GB GPU memory using the AirLLM framework, making cutting-edge AI technology accessible to users with limited hardware resources. (本文展示了如何利用AirLLM框架，在仅4GB GPU内存的条件下运行强大的Llama3 70B开源大语言模型，使硬件资源有限的用户也能接触前沿AI技术。)

AI大模型2026/1/24

阅读全文 →

AirLLM：单卡4GB显存运行700亿大模型，革命性轻量化框架

BLUFAirLLM is an innovative lightweight framework that enables running 70B parameter large language models on a single 4GB GPU through advanced memory optimization techniques, significantly reducing hardware costs while maintaining performance. (AirLLM是一个创新的轻量化框架，通过先进的内存优化技术，可在单张4GB GPU上运行700亿参数的大语言模型，大幅降低硬件成本的同时保持性能。)

AI大模型2026/1/24

阅读全文 →

UltraRAG 2.0：基于MCP架构的低代码高性能RAG框架，让复杂推理系统开发效率提升20倍

BLUFUltraRAG 2.0 is a novel RAG framework built on the Model Context Protocol (MCP) architecture, designed to drastically reduce the engineering overhead of implementing complex multi-stage reasoning systems. It achieves this through componentized encapsulation and YAML-based workflow definitions, enabling developers to build advanced systems with as little as 5% of the code required by traditional frameworks, while maintaining high performance and supporting features like dynamic retrieval and conditional logic. UltraRAG 2.0 是一个基于模型上下文协议（MCP）架构设计的新型RAG框架，旨在显著降低构建复杂多阶段推理系统的工程成本。它通过组件化封装和YAML流程定义，使开发者能够用传统框架所需代码量的5%即可构建高级系统，同时保持高性能，并支持动态检索、条件判断等功能。

AI大模型2026/1/24

阅读全文 →

OpenBMB：清华大学开源社区如何推动大语言模型高效计算与参数微调

BLUFOpenBMB is an open-source community and toolset initiated by Tsinghua University since 2018, focused on building efficient computational tools for large-scale pre-trained language models. Its core contribution includes parameter-efficient fine-tuning methods, and it has released significant projects like UltraRAG 2.1, UltraEval-Audio v1.1.0, and the 4-billion-parameter AgentCPM-Explore model, which demonstrate strong performance in benchmarks. (OpenBMB是清华大学自2018年起支持发起的开源社区与工具集，致力于构建大规模预训练语言模型的高效计算工具。其核心贡献包括参数高效微调方法，并发布了UltraRAG 2.1、UltraEval-Audio v1.1.0和40亿参数的AgentCPM-Explore模型等重要项目，在多项基准测试中表现出色。)

AI大模型2026/1/24

阅读全文 →

上一页 1...49 50 51 52 53...94 下一页