{"id":19802,"date":"2024-09-12T09:44:56","date_gmt":"2024-09-12T01:44:56","guid":{"rendered":"https:\/\/www.1ai.net\/?p=19802"},"modified":"2024-09-12T09:44:56","modified_gmt":"2024-09-12T01:44:56","slug":"pixtral-12b-%e5%8f%91%e5%b8%83%ef%bc%9amistral%e5%bc%80%e6%ba%90%e9%a6%96%e4%b8%aa%e5%a4%9a%e6%a8%a1%e6%80%81ai%e5%a4%a7%e6%a8%a1%e5%9e%8b","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/19802.html","title":{"rendered":"Pixtral 12B Released: Mistral Open Sources First Multimodal AI Big Model"},"content":{"rendered":"

\u79d1\u6280\u5a92\u4f53 TechCrunch \u6628\u65e5\uff089 \u6708 11 \u65e5\uff09\u62a5\u9053\uff0c\u6cd5\u56fd<\/a> AI \u521d\u521b\u516c\u53f8<\/a> Mistral<\/a> \u53d1\u5e03 Pixtral 12B\uff0c\u662f\u8be5\u516c\u53f8\u9996\u6b3e\u80fd\u591f\u540c\u65f6\u5904\u7406\u56fe\u50cf\u548c\u6587\u672c\u7684\u591a\u6a21\u6001 AI\u5927\u8bed\u97f3\u6a21\u578b\u3002<\/strong><\/p>\n

Pixtral 12B \u6a21\u578b\u62e5\u6709 120 \u4ebf\u53c2\u6570\uff0c\u5927\u5c0f\u7ea6\u4e3a 24GB\uff0c\u53c2\u6570\u5927\u81f4\u5bf9\u5e94\u4e8e\u6a21\u578b\u7684\u89e3\u9898\u80fd\u529b\uff0c\u62e5\u6709\u66f4\u591a\u53c2\u6570\u7684\u6a21\u578b\u901a\u5e38\u6bd4\u53c2\u6570\u8f83\u5c11\u7684\u6a21\u578b\u8868\u73b0\u66f4\u4f18\u3002<\/p>\n

Pixtral 12B \u6a21\u578b\u57fa\u4e8e\u6587\u672c\u6a21\u578b Nemo 12B \u6784\u5efa\uff0c\u80fd\u591f\u56de\u7b54\u5173\u4e8e\u4efb\u610f\u6570\u91cf\u3001\u4efb\u610f\u5c3a\u5bf8\u56fe\u50cf\u7684\u95ee\u9898\u3002<\/p>\n

\u4e0e Anthropic \u7684 Claude \u7cfb\u5217\u548c OpenAI \u7684 GPT-4o \u7b49\u5176\u4ed6\u591a\u6a21\u6001\u6a21\u578b\u7c7b\u4f3c\uff0cPixtral 12B \u7406\u8bba\u4e0a\u5e94\u80fd\u6267\u884c\u8bf8\u5982\u4e3a\u56fe\u50cf\u6dfb\u52a0\u63cf\u8ff0\u548c\u7edf\u8ba1\u7167\u7247\u4e2d\u7269\u4f53\u6570\u91cf\u7b49\u4efb\u52a1\u3002<\/p>\n

\u7528\u6237\u53ef\u4ee5\u4e0b\u8f7d\u3001\u5fae\u8c03 Pixtral 12B \u6a21\u578b\uff0c\u5e76\u80fd\u4f9d\u636e Apache 2.0 \u8bb8\u53ef\u8bc1\u4f7f\u7528\u3002<\/p>\n

Mistral \u5f00\u53d1\u8005\u5173\u7cfb\u8d1f\u8d23\u4eba Sophia Yang \u5728 X \u5e73\u53f0\u7684\u4e00\u7bc7\u5e16\u5b50\u4e2d\u8868\u793a\uff0cPixtral 12B \u5f88\u5feb\u5c06\u5728 Mistral \u7684\u804a\u5929\u673a\u5668\u4eba\u548c API \u670d\u52a1\u5e73\u53f0 Le Chat \u53ca Le Plateforme \u4e0a\u5f00\u653e\u6d4b\u8bd5\u3002<\/p>\n

\"b1169173j00sjof9k003xd000hb00a4m\"<\/p>\n

\u5728\u6280\u672f\u89c4\u683c\u4e0a\uff0cPixtral12B\u540c\u6837\u4ee4\u4eba\u5370\u8c61\u6df1\u523b:40\u5c42\u7f51\u7edc\u7ed3\u6784\u300114\uff0c336\u4e2a\u9690\u85cf\u7ef4\u5ea6\u300132\u4e2a\u6ce8\u610f\u529b\u5934\uff0c\u4ee5\u53ca400M\u7684\u4e13\u7528\u89c6\u89c9\u7f16\u7801\u5668\uff0c\u652f\u6301\u5904\u74061024×1024\u5206\u8fa8\u7387\u7684\u56fe\u50cf\u3002<\/p>\n

\"c23e1309j00sjof9l004rd000gs007ym\"<\/p>\n

\u5728MMMU\u3001Mathvista\u3001ChartQA\u3001DocVQA\u7b49\u5e73\u53f0\u4e0a\uff0c\u5b83\u7684\u6210\u7ee9\u8d85\u8d8a\u4e86\u5305\u62ecPhi-3\u548cQwen-27B\u5728\u5185\u7684\u591a\u4e2a\u77e5\u540d\u591a\u6a21\u6001\u6a21\u578b\uff0c\u5145\u5206\u8bc1\u660e\u4e86\u5176\u5f3a\u52b2\u7684\u5b9e\u529b\u3002<\/p>\n

huggingface\u5730\u5740:<\/p>\n

https:\/\/huggingface.co\/mistral-community\/pixtral-12b-240910<\/p>\n","protected":false},"excerpt":{"rendered":"

TechCrunch reported yesterday (September 11) that French AI startup Mistral has released Pixtral 12B, the company's first multimodal AI big speech model capable of processing images and text simultaneously. The Pixtral 12B model has 12 billion parameters, or about 24GB in size, and the parameters roughly correspond to the model's problem-solving ability, with models with more parameters generally performing better than those with fewer parameters. The Pixtral 12B model is based on the textual model Nemo 12B, and is capable of answering questions about any number of images of any size. It is similar to Anthropic's Claude series and OpenAI's<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[146],"tags":[559,309,602,2529],"collection":[],"class_list":["post-19802","post","type-post","status-publish","format-standard","hentry","category-news","tag-mistral","tag-309","tag-602","tag-2529"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/19802","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=19802"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/19802\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=19802"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=19802"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=19802"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=19802"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}