<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic DBRX vs GPT4 in Generative AI</title>
    <link>https://community.databricks.com/t5/generative-ai/dbrx-vs-gpt4/m-p/72995#M159</link>
    <description>&lt;P&gt;Which is the best&lt;/P&gt;</description>
    <pubDate>Wed, 12 Jun 2024 19:25:40 GMT</pubDate>
    <dc:creator>Kk17</dc:creator>
    <dc:date>2024-06-12T19:25:40Z</dc:date>
    <item>
      <title>DBRX vs GPT4</title>
      <link>https://community.databricks.com/t5/generative-ai/dbrx-vs-gpt4/m-p/72995#M159</link>
      <description>&lt;P&gt;Which is the best&lt;/P&gt;</description>
      <pubDate>Wed, 12 Jun 2024 19:25:40 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/dbrx-vs-gpt4/m-p/72995#M159</guid>
      <dc:creator>Kk17</dc:creator>
      <dc:date>2024-06-12T19:25:40Z</dc:date>
    </item>
    <item>
      <title>Re: DBRX vs GPT4</title>
      <link>https://community.databricks.com/t5/generative-ai/dbrx-vs-gpt4/m-p/73001#M160</link>
      <description>&lt;P&gt;Dbrx&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Wed, 12 Jun 2024 19:27:39 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/dbrx-vs-gpt4/m-p/73001#M160</guid>
      <dc:creator>SathishAI24</dc:creator>
      <dc:date>2024-06-12T19:27:39Z</dc:date>
    </item>
    <item>
      <title>Re: DBRX vs GPT4</title>
      <link>https://community.databricks.com/t5/generative-ai/dbrx-vs-gpt4/m-p/76697#M225</link>
      <description>&lt;P&gt;Hi&amp;nbsp;&lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/107417"&gt;@Kk17&lt;/a&gt;&amp;nbsp;, it really depends on what you value most. If you value leaderboard scores and model output quality above all else, then &lt;A href="https://huggingface.co/spaces/ArtificialAnalysis/LLM-Performance-Leaderboard" target="_self"&gt;GPT-4 is generally the stronger&lt;/A&gt;&amp;nbsp;of the two models. However, GPT-4 also costs nearly $40 per million tokens, your requests and responses need to be sent to a proprietary third party model, and you cannot fine tune the model on your own data.&amp;nbsp;&lt;/P&gt;
&lt;P&gt;DBRX, by contrast, is slightly lower in model performance out of the box, but can be fine tuned - either on Databricks or on another platform - to achieve performance even higher than that of GPT-4 on the tasks that you care about most. DBRX can be downloaded locally and served from any sufficiently large machine. It also costs substantially less, at around $1+ per million tokens when self served and has a context window that is 4x longer than GPT-4: nearly 33k tokens vs 8k.&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 04 Jul 2024 00:28:38 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/dbrx-vs-gpt4/m-p/76697#M225</guid>
      <dc:creator>AustinZaccor</dc:creator>
      <dc:date>2024-07-04T00:28:38Z</dc:date>
    </item>
  </channel>
</rss>

