{"id":22896,"date":"2024-11-12T01:52:57","date_gmt":"2024-11-11T17:52:57","guid":{"rendered":"https:\/\/www.1ai.net\/?p=22896"},"modified":"2024-11-11T20:54:24","modified_gmt":"2024-11-11T12:54:24","slug":"ai-%e5%88%9d%e5%88%9b%e5%85%ac%e5%8f%b8%e6%8e%a8%e5%87%ba-nous-chat-%e8%81%8a%e5%a4%a9%e6%9c%ba%e5%99%a8%e4%ba%ba%ef%bc%8c%e5%ba%95%e5%b1%82%e5%9f%ba%e4%ba%8e-meta-llama-3-1-%e6%89%93%e9%80%a0","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/22896.html","title":{"rendered":"AI startup launches Nous Chat chatbot, built on Meta Llama 3.1 underpinnings"},"content":{"rendered":"<p>AI <a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%88%9d%e5%88%9b%e5%85%ac%e5%8f%b8\" title=\"[Sees articles with labels]\" target=\"_blank\" >Startups<\/a> Nous Research has recently launched a new product called\u00a0<a href=\"https:\/\/www.1ai.net\/en\/tag\/nous-chat\" title=\"[Sees articles with [Nos Chat] label]\" target=\"_blank\" >Nous Chat<\/a> of AI <a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%81%8a%e5%a4%a9%e6%9c%ba%e5%99%a8%e4%ba%ba\" title=\"[View articles tagged with [chatbot]]\" target=\"_blank\" >Chatbots<\/a>,<strong>The robot is based on the Meta Llama 3.1 fine-tuned \"Hermes 3-70B\" model.<\/strong>The company claims to be committed to \"human-centeredness\" with deep improvements in \"model architecture, data synthesis, fine-tuning and inference\".<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-22897\" title=\"87319d84j00smsegy00lgd000v900g9p\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/11\/87319d84j00smsegy00lgd000v900g9p.jpg\" alt=\"87319d84j00smsegy00lgd000v900g9p\" width=\"1125\" height=\"585\" \/><\/p>\n<p>It is reported that Nous Chat robot has the functions of long pulse memory, multi-round conversation, complex role-playing and self-monologue, etc. At present, Nous Research has also opened the related Hermes 3-70B model family in Hugging Face for developers to preview, and the organizing address of the project is as follows.<a href=\"https:\/\/huggingface.co\/NousResearch\/Hermes-3-Llama-3.1-70B\">Click here to visit<\/a>).<\/p>\n<p>Nous Research also previewed a model called Nous-Hermes-2-Mixtral-8x7B-DPO, an expert mixing model based on Mixtral 8x7B, which is claimed to be able to deliver a multi-character experience using a large amount of data generated by GPT-4 and other open source datasets for training.<\/p>\n<p>In addition to this, the company also announced a Nous-Capybara-7B V1.9 built on the Mistral architecture, which is claimed to be trained on 20,000 conversations, giving it a major advantage in terms of conversational naturalness and coherence.<\/p>\n<p>In terms of Nous Chat, the overall interface of the bot is not much different from that of ChatGPT and Claude.<strong>Can communicate in English, Chinese, Japanese, and other languages, and the corresponding chatbot's knowledge deadline is April 2023<\/strong>However, the chatbot does not have the programming capabilities of mainstream AI models, and there is still room for improvement.<\/p>","protected":false},"excerpt":{"rendered":"<p>AI startup Nous Research recently launched an AI chatbot called Nous Chat, which is based on the \"Hermes 3-70B\" model fine-tuned with Meta Llama 3.1, and is claimed to have made deep improvements in \"model architecture, data synthesis and inference, The robot is based on the \"Hermes 3-70B\" model fine-tuned from Meta Llama 3.1, and is said to have made in-depth improvements in \"model architecture, data synthesis, fine-tuning, and inference\", and is committed to being \"human-centric\". It is reported that the Nous Chat robot is equipped with functions such as long pulse memory, multi-round conversations, complex role-playing and self-monologue, etc. At present, Nous Research has also opened up the relevant Hermes 3-70B model family for developers to preview on Hugging Face, and the address of the organizing project is as follows (click here)<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[4901,309,275],"collection":[],"class_list":["post-22896","post","type-post","status-publish","format-standard","hentry","category-news","tag-nous-chat","tag-309","tag-275"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/22896","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=22896"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/22896\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=22896"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=22896"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=22896"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=22896"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}