Trends Artificial Intelligence
multimodality across audio, visual, & text inputs 7/24: Apple releases Apple Intelligence, an AI system integrated into its devices, for developers 12/24: OpenAI announces o3, its highest-ever designate particularly influential models within the AI/machine learning ecosystem. Epoch maintains a database of 900 AI models released since the 1950s, selecting entries based on criteria such as state-of-the-art Unprecedented41 AI Performance = In 2024… Surpassed Human Levels of Accuracy & Realism, per Stanford HAI AI System Performance on MMLU Benchmark Test – 2019-2024, per Stanford HAI Note: The MMLU (Massive Multitask0 码力 | 340 页 | 12.14 MB | 4 月前3
OpenAI 《A practical guide to building agents》Well-documented, thoroughly tested, and reusable tools improve discoverability, simplify version management, and prevent redundant definitions. Broadly speaking, agents need three types of tools: Type Description complicated instructions or consistently select incorrect tools, you may need to further divide your system and introduce more distinct agents. Practical guidelines for splitting agents include: Complex r] ) order_management_agent = Agent( name= , instructions=( "Technical Support Agent", "You provide expert assistance with resolving technical issues, system outages, or product0 码力 | 34 页 | 7.00 MB | 6 月前3
Google 《Prompt Engineering v7》Prompting techniques 13 General prompting / zero shot 13 One-shot & few-shot 15 System, contextual and role prompting 18 System prompting 19 Role prompting 21 Contextual prompting 23 Table of contents February 2025 18 System, contextual and role prompting System, contextual and role prompting are all techniques used to guide how LLMs generate text, but they focus on different aspects: • System prompting sets and behavior. There can be considerable overlap between system, contextual, and role prompting. E.g. a prompt that assigns a role to the system, can also have a context. However, each type of prompt serves0 码力 | 68 页 | 6.50 MB | 6 月前3
Manus AI:Agent元年开启»4 AI *+¼½()> • 9⃣ ETL«]^á²2¾¿¬5š›]^¥+CA+,ñ AI *+ÇÀÁ%WO> • *˜5DATAVOLOcNeedlecVerdat> • 🔟 ]^«Database¬5•‘C¥+ AI *+GÕÂÍÄÅ]^> • *˜5ChromacDrantcSupabasecPinecone«Æ¥]^¬ÇMongoDBc PostgreSQLcWeaviatecNeo4j«Å AgentŸ Ö×AgentS) cCÕ 'Agent ØCKx¦13 !"#$%Bloomberg*&'() >$2%AgentFG?@HIJKLM p Workday#$ Agent System of Record ! Workday #$G AI *+«AI Agents¬¥+,-,-G¼½ŒÙ! QŸcC¥+c4ÚC ªÛ®‰ AI *+«AI-powered agents¬,ÜÝÞß*+0 码力 | 23 页 | 4.87 MB | 5 月前3
OpenAI - AI in the Enterpriseof NPS surveys. 16 AI in the EnterpriseAnd the wins continue to spread across Marketing, Risk Management, Operations, and beyond. All because they got AI in the hands of the people who know how to apply thousands of tasks every month, freeing people to do more high-impact work. Not surprisingly, the system is now spreading across other departments. It happened because we set bold automation goals from0 码力 | 25 页 | 9.48 MB | 5 月前3
开源中国 2023 大模型(LLM)技术报告方法为语言任务提供了前所未有的性能,以此为基础,多模态融合的应用使得 LLM 更全面地处理各种 信息,支持更广泛的应用领域。 图源:https://postgresml.org/docs/.gitbook/assets/ml_system.svg 4 / 32 LLM 基础设施 01 03 02 04 向量数据库/数据库向量支持 为大模型提供高效的存储和检索能力 大模型框架及微调 (Fine Tuning) 年前四个月,向量数据库公司融资额 ,超过了 2022 年的总和 (图源:https://www.cbinsights.com/research/generative-ai-infrastructure- vector-database/) 7 / 32 LLM 基础设施:大模型框架及微调 (Fine Tuning) 大模型框架指专门设计用于构建、训练和部署大型机器 学习模型和深度学习模型的软件框架。这些框架提供了 必0 码力 | 32 页 | 13.09 MB | 1 年前3
DeepSeek-V2: A Strong, Economical, and Efficient
Mixture-of-Experts Language ModelZhuang, Y. Sheng, L. Zheng, C. H. Yu, J. E. Gonzalez, H. Zhang, and I. Stoica. Efficient memory management for large language model serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium n&=480/30=\boxed{16} \end{align*} Final Answer: The final answer is $16$. I hope it is correct. Problem: If the system of equations \begin{align*} 6x-4y&=a,\\ 6y-9x &=b. \end{align*}has a solution $(x, y)$ where $x$0 码力 | 52 页 | 1.23 MB | 1 年前3
亿联TVM部署TRUE); if (ret == WAIT_OBJECT_0) { cout << " Thread " << GetCurrentThreadId() << "writing to database...\n" << endl; } else if (ret == WAIT_ABANDONED) { cout << "Thread failed ...\n" << endl; }0 码力 | 6 页 | 1.96 MB | 5 月前3
00 Deepseek官方提示词更多 Deepseek 和 AI 资料,欢迎关注微信公众号【星禾光年 AI】,回复【deepseek】获取 1. 万能提示词生成模版:根据用户需求,帮助生成高质量提示词 SYSTEM 你是一位大模型提示词生成专家,请根据用户的需求编写一个智能助手的提示词,来指导大模型进行内容生成, 要求: 1. 以 Markdown 格式输出 2. 贴合用户需求,描述智能助手的定位、能力、知识储备 3 提示词应清晰、精确、易于理解,在保持质量的同时,尽可能简洁 4. 只输出提示词,不要输出多余解释 USER “ 请帮我生成一个 Linux ” 助手 的提示词 2. 文案大纲生成:根据用户提供的主题,来生成文案大纲 SYSTEM 你是一位文本大纲生成专家,擅长根据用户的需求创建一个有条理且易于扩展成完整文章的大纲,你拥有强大的 主题分析能力,能准确提取关键信息和核心要点。具备丰富的文案写作知识储备,熟悉各种文体和题材的文案大 创意性标题:为文章构思一个引人注目的标题,确保它既反映了文章的核心内容又能激发读者的好奇心。 USER “ ” 请帮我生成 中国农业情况 这篇文章的大纲 3. 中英翻译专家:中英文互译,对用户输入内容进行翻译 SYSTEM 你是一个中英文翻译专家,将用户输入的中文翻译成英文,或将用户输入的英文翻译成中文。对于非中文内容, 它将提供中文翻译结果。用户可以向助手发送需要翻译的内容,助手会回答相应的翻译结果,并确保符合中文语0 码力 | 4 页 | 7.93 KB | 8 月前3
Bring Your Own Codegen to TVMHow Would That Look Like?© 2019, Amazon Web Services, Inc. or its Affiliates. All rights reserved. System Overview Relay IR Graph Annotation with Your Annotator Graph Partitioning Your Codegen LLVM Inc. or its Affiliates. All rights reserved. Partition the Relay IR graph ● No user involvement System Overview Relay IR Graph Annotation with Your Annotator Graph Partitioning Your Codegen LLVM Inc. or its Affiliates. All rights reserved. Partition the Relay IR graph ● No user involvement System Overview Relay IR Graph Annotation with Your Annotator Graph Partitioning Your Codegen LLVM0 码力 | 19 页 | 504.69 KB | 5 月前3
共 16 条
- 1
- 2













