{"id":8060,"date":"2024-04-16T09:46:50","date_gmt":"2024-04-16T01:46:50","guid":{"rendered":"https:\/\/www.1ai.net\/?p=8060"},"modified":"2024-04-16T09:46:50","modified_gmt":"2024-04-16T01:46:50","slug":"%e9%9d%a2%e5%a3%81%e6%99%ba%e8%83%bd%e5%bc%80%e6%ba%90minicpm-2-0%e7%b3%bb%e5%88%97%e6%a8%a1%e5%9e%8b-ocr%e7%ad%89%e8%83%bd%e5%8a%9b%e6%98%be%e8%91%97%e5%a2%9e%e5%bc%ba","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/8060.html","title":{"rendered":"The open source MiniCPM 2.0 series of models from Mianbi Intelligent has significantly enhanced its OCR and other capabilities"},"content":{"rendered":"<p><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e9%9d%a2%e5%a3%81%e6%99%ba%e8%83%bd\" title=\"[View articles tagged with [face smart]]\" target=\"_blank\" >Wall-facing intelligence<\/a><span class=\"spamTxt\">up to date<\/span>The new generation of flagship edge-side models launched by the company - the MiniCPM2.0 series models bring a series of amazing performance and features:<\/p>\n<p>1. MiniCPM-V2.0 is on the end side<span class=\"spamTxt\">Strongest<\/span>of<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%a4%9a%e6%a8%a1%e6%80%81%e6%a8%a1%e5%9e%8b\" title=\"[View articles tagged with [multimodal model]]\" target=\"_blank\" >Multimodal Model<\/a>, with powerful OCR capabilities, even comparable to Gemini Pro in some aspects. It uses self-developed high-definition image decoding technology to accurately recognize various complex image contents, including street scenes and long images.<\/p>\n<p>2. MiniCPM-1.2B is a base model that is more suitable for edge scenarios. Its performance exceeds many mainstream models, including Llama2-13B. Its inference speed is nearly 25 times the human speaking speed, and its cost is also greatly reduced.<\/p>\n<p>3. MiniCPM-2B-128K is currently the smallest long text model, which can process 128K (200,000 words) of text content and performs excellently on the multi-dimensional long text evaluation set.<\/p>\n<p>4. MiniCPM-MoE-8x2B is a MoE architecture model with further enhanced performance, with an average performance improvement of 4.5 percentage points and an inference cost of only 69.7% of Gemini-7B.<\/p>\n<p class=\"article-content__img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-8061\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/04\/6384877010877470639337654.jpg\" alt=\"\" width=\"293\" height=\"655\" \/><\/p>\n<p>These new-generation MiniCPM models have demonstrated powerful performance and functionality in different fields and scenarios, promoting the further development of large models in terminal applications. At the same time, Mianbi Intelligence has just completed a new round of financing of hundreds of millions of yuan, and plans to continue the journey of efficient large models for AGI, and welcomes outstanding talents to join their team.<\/p>\n<p><strong>MiniCPM-V2.0:<\/strong><\/p>\n<p>https:\/\/github.com\/OpenBMB\/MiniCPM-V<\/p>\n<p><strong>MiniCPM Series<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bc%80%e6%ba%90\" title=\"[View articles tagged with [open source]]\" target=\"_blank\" >Open Source<\/a>address:<\/strong><\/p>\n<p>https:\/\/github.com\/OpenBMB\/MiniCPM<\/p>\n<p><strong>MiniCPM<\/strong><strong>Technical blog address:<\/strong><\/p>\n<p>https:\/\/openbmb.vercel.app\/?category=Chinese+Blog<\/p>","protected":false},"excerpt":{"rendered":"<p>The latest flagship end-side model of the new generation launched by Faceted Intelligence -- Faceted MiniCPM2.0 series models bring a series of amazing performance and features: 1. MiniCPM-V2.0 is the strongest multimodal model on the end-side, with powerful OCR capabilities, and even some of them are comparable to the capabilities of Gemini With its self-developed HD image decoding technology, it can accurately recognize all kinds of complex image contents, including street view and long image, etc. 2. 2. MiniCPM-1.2B is a base model that is more suitable for end-side scenarios and outperforms many mainstream models, including Llama2-13B. Its inference speed reaches nearly 25 times of human speech speed, and the cost is reduced dramatically. 3. MiniCPM-2B-128K<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[1096,219,2184],"collection":[],"class_list":["post-8060","post","type-post","status-publish","format-standard","hentry","category-news","tag-1096","tag-219","tag-2184"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/8060","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=8060"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/8060\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=8060"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=8060"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=8060"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=8060"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}