参数量42亿，微软公布SLM小语言AI模型最新成员Phi-3-vision

IT之家05-26

IT之家 5 月 26 日消息，微软近日公布了旗下小语言 AI 模型家族（SLM）最新成员“Phi-3-vision”，这款模型主打“视觉能力”，能够理解图文内容，同时据称可以在移动平台上流畅高效运行。据介绍，Phi-3-vision 是微软 Phi-3 家族首款多模态模型，该模型的文字理解能力基于 Phi-3-mini，同时也具备 Phi-3-mini 的轻量特点，能够在移动平台 / 嵌入终端中...

网页链接

免责声明：本文观点仅代表作者个人观点，不构成本平台的投资建议，本平台不对文章信息准确性、完整性和及时性做出任何保证，亦不对因使用或信赖文章信息引发的任何损失承担责任。

精彩评论

我们需要你的真知灼见来填补这片空白

发表看法

{"i18n":{"language":"zh_CN"},"isChannel":false,"data":{"share":"https://www.laohu8.com/m/news/2438740832?lang=zh_CN&edition=full","thumbnail":"","is_english":false,"pubTime":"2024-05-26 12:49","share_image_url":"https://static.laohu8.com/e9f99090a1c2ed51c021029395664489","id":"2438740832","market":"hk","top_or_hot":-1,"title":"参数量42亿，微软公布SLM小语言AI模型最新成员Phi-3-vision","media":"IT之家","content":"<div>\n<p>IT之家 5 月 26 日消息，微软近日公布了旗下小语言 AI 模型家族（SLM）最新成员“Phi-3-vision”，这款模型主打“视觉能力”，能够理解图文内容，同时据称可以在移动平台上流畅高效运行。据介绍，Phi-3-vision 是微软 Phi-3 家族首款多模态模型，该模型的文字理解能力基于 Phi-3-mini，同时也具备 Phi-3-mini 的轻量特点，能够在移动平台 / 嵌入终端中...</p>\n\n<a href=\"https://tech.ifeng.com/c/8ZtKfeSPIie\">网页链接</a>\n\n</div>\n","source":"ifeng_tech","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>参数量42亿，微软公布SLM小语言AI模型最新成员Phi-3-vision</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 11px; color: #7E829C; margin: 0;line-height: 11px;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\n参数量42亿，微软公布SLM小语言AI模型最新成员Phi-3-vision\n</h2>\n\n<h4 class=\"meta\">\n\n\n2024-05-26 12:49 北京时间&nbsp;&nbsp;&nbsp;<a href=https://tech.ifeng.com/c/8ZtKfeSPIie><strong>IT之家</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>IT之家 5 月 26 日消息，微软近日公布了旗下小语言 AI 模型家族（SLM）最新成员“Phi-3-vision”，这款模型主打“视觉能力”，能够理解图文内容，同时据称可以在移动平台上流畅高效运行。据介绍，Phi-3-vision 是微软 Phi-3 家族首款多模态模型，该模型的文字理解能力基于 Phi-3-mini，同时也具备 Phi-3-mini 的轻量特点，能够在移动平台 / 嵌入终端中...</p>\n\n<a href=\"https://tech.ifeng.com/c/8ZtKfeSPIie\">网页链接</a>\n\n</div>\n\n\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"IE00B7KXQ091.USD","symbol_name":"Janus Henderson Balanced A Inc USD","start_time":0,"source_url":"https://tech.ifeng.com/c/8ZtKfeSPIie","article_id":"2438740832","we_media_id":null,"thumbnails":[],"rights":null,"url":"https://stock-news.laohu8.com/highlight/detail?id=2438740832","pubTimestamp":1716698996,"sourceInfo":{"source_id":"ifeng_tech","name":"凤凰网财经"},"weMediaInfo":null,"summary":"IT之家 5 月 26 日消息，微软近日公布了旗下小语言 AI 模型家族最新成员“Phi-3-vision”，这款模型主打“视觉能力”，能够理解图文内容，同时据称可以在移动平台上流畅高效运行。在模型训练方面，微软声称 Phi-3-vision 是由“多种类型图片及文字数据训练而成”，包括一系列“经过严选的公开内容”，例如“教科书等级”教育材料、代码、图文标注数据、现实世界知识、图表图片、聊天格式等内容，从而确保模型输入内容的多样性。","collect":0,"end_time":0,"defaultTopTitle":"ifeng.com","property":[],"viewcount":null,"language":"zh","relate_stocks":{"IE00B7KXQ091.USD":"Janus Henderson Balanced A Inc USD","IE0009356076.USD":"JANUS HENDERSON GLOBAL TECHNOLOGY AND INNOVATION \"A2\" (USD) ACC","BK4548":"巴美列捷福持仓","IE00B775SV38.USD":"NEUBERGER BERMAN US MULTICAP OPPORTUNITIES \"A\" (USD) ACC","SLM":"学贷美","LU0109391861.USD":"富兰克林美国机遇基金A Acc","IE00B3S45H60.SGD":"Neuberger Berman US Multicap Opportunities A Acc SGD-H","IE0004445239.USD":"JANUS HENDERSON US FORTY \"A2\" (USD) ACC","IE00B19Z9505.USD":"美盛-美国大盘成长股A Acc","IE0034235295.USD":"PINEBRIDGE GLOBAL DYNAMIC ASSET ALLOCATION \"A\" (USD) ACC","BK4516":"特朗普概念","IE00BJJMRX11.SGD":"Janus Henderson Balanced A Acc SGD","IE00BJTD4V19.USD":"NEUBERGER BERMAN US LONG SHORT EQUITY \"A1\" (USD) ACC","BK4554":"元宇宙及AR概念","BK4532":"文艺复兴科技持仓","IE00BDCRKT87.USD":"PINEBRIDGE GLOBAL DYNAMIC ASSET ALLOCATION \"ADC\" (USD) INC","GB00BDT5M118.USD":"天利环球扩展Alpha基金A Acc","LU0079474960.USD":"联博美国增长基金A","IE00B1XK9C88.USD":"PINEBRIDGE US LARGE CAP RESEARCH ENHANCED \"A\" (USD) ACC","GB00B4QBRK32.GBP":"FUNDSMITH EQUITY \"R\" (GBP) INC","BK4567":"ESG概念","BK4534":"瑞士信贷持仓","GB00B4LPDJ14.GBP":"FUNDSMITH EQUITY \"R\" (GBP) ACC","LU0061474960.USD":"天利环球焦点基金AU Acc","MSFT":"微软","IE00BJJMRY28.SGD":"Janus Henderson Balanced A Inc SGD","BK4533":"AQR资本管理(全球第二大对冲基金)","IE00BBT3K403.USD":"LEGG MASON CLEARBRIDGE TACTICAL DIVIDEND INCOME \"A(USD) ACC","IE00BKDWB100.SGD":"PINEBRIDGE US LARGE CAP RESEARCH ENHANCED \"A5H\" (SGDHDG) ACC","LU0171293334.USD":"贝莱德英国基金A2","LU0109392836.USD":"富兰克林科技股A","BK4566":"资本集团","LU2517655028.SGD":"WELLINGTON NEXT GENERATION EDUCATION \"A\" (SGDHDG) ACC","BK4535":"淡马锡持仓","IE0004445015.USD":"JANUS HENDERSON BALANCED \"A2\" (USD) ACC","LU2517655291.USD":"WELLINGTON NEXT GENERATION EDUCATION \"A\" (USD) ACC","BK4538":"云计算","LU0175139822.USD":"AB FCP I Global Equity Blend A USD","LU0011850046.USD":"贝莱德全球长线股票 A2 USD","LU0149725797.USD":"汇丰美国股市经济规模基金","LU2517655374.HKD":"WELLINGTON NEXT GENERATION EDUCATION \"A\" (HKD) ACC","LU0097036916.USD":"贝莱德美国增长A2 USD","BK4550":"红杉资本持仓","IE00B1BXHZ80.USD":"Legg Mason ClearBridge - US Appreciation A Acc USD","LU0061475181.USD":"THREADNEEDLE (LUX) AMERICAN \"AU\" (USD) ACC","IE0034235188.USD":"PINEBRIDGE GLOBAL FOCUS EQUITY \"A\" (USD) ACC","BK4097":"系统软件","LU0127658192.USD":"EASTSPRING INVESTMENTS GLOBAL TECHNOLOGY \"A\" (USD) ACC","IE00BKVL7J92.USD":"Legg Mason ClearBridge - US Equity Sustainability Leaders A Acc USD","IE00BJTD4N35.SGD":"Neuberger Berman US Long Short Equity A1  Acc SGD-H"},"translate_title":"With 4.2 billion parameters, Microsoft announced the latest member of the SLM small language AI model, Phi-3-vision","themeId":null,"isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"SLM":1,"MSFT":1},"content_text":"IT之家 5 月 26 日消息，微软近日公布了旗下小语言 AI 模型家族（SLM）最新成员“Phi-3-vision”，这款模型主打“视觉能力”，能够理解图文内容，同时据称可以在移动平台上流畅高效运行。据介绍，Phi-3-vision 是微软 Phi-3 家族首款多模态模型，该模型的文字理解能力基于 Phi-3-mini，同时也具备 Phi-3-mini 的轻量特点，能够在移动平台 / 嵌入终端中运行；该模型参数量为 42 亿，大于 Phi-3-mini（3.8B），但小于 Phi-3-small（7B），上下文长度为 128k token，训练期间为 2024 年 2 月至 4 月。IT之家注意到，Phi-3-vision 模型的最大特色正如其名，主要支持“图文识别能力”，号称能够理解现实世界的图片含义，还能快速识别提取图片中的文字。微软表示，Phi-3-vision 特别适合办公场合，开发人员特别优化了该模型在识别图表和方块图 (Block diagram) 方面的理解能力，据称可以利用用户输入的信息进行推论，同时还能做出一系列结论，为企业提供战略建议，号称“效果比肩大模型”。在模型训练方面，微软声称 Phi-3-vision 是由“多种类型图片及文字数据训练而成”，包括一系列“经过严选的公开内容”，例如“教科书等级”教育材料、代码、图文标注数据、现实世界知识、图表图片、聊天格式等内容，从而确保模型输入内容的多样性。为了确保隐私，微软声称他们所使用的训练数据“可追溯”不包含任何个人信息。性能方面，微软提供了 Phi-3-vision 相较于字节跳动 Llama3-Llava-Next（8B）、微软研究院和威斯康星大学、哥伦比亚大学合作的 LlaVA-1.6（7B）、阿里巴巴通义千问 QWEN-VL-Chat 模型等竞品模型的比较图表，其中显示 Phi-3-vision 模型在多个项目上表现优异。","kind":null,"is_publish_news":true,"is_publish_highlight":false,"is_publish_live":null,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"0","news_tag":"","news_rank":0,"symbols":[],"gpt_button":1},"commentList":[],"isCommentEnd":true,"newsSizeData":{"likeSize":0,"commentSize":0,"repostSize":0,"favoriteSize":0,"likeStatus":false,"favoriteStatus":false},"APP":{"userAgent":"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)","isDev":false,"isTTM":false,"deviceId":"web-server-community-laohu8-v3","version":"4.25.1","shortVersion":"4.25.1","platform":"web","vendor":"web","appName":"laohu8","isIOS":false,"isAndroid":false,"isTiger":false,"isTHS":false,"isWeiXin":false,"isWeiXinMini":false,"isWeiBo":false,"isQQ":false,"isBaiduSwan":false,"isBaiduBox":false,"isDingTalk":false,"isToutiao":false,"isOnePlus":false,"isHuaWei":false,"isXiaomi":false,"isXiaomiWebView":false,"isOppo":false,"isVivo":false,"isSamsung":false,"isMobile":false},"href":"/m/news/2438740832"}