<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>GCP on Prakash&#39;s Blog 👨‍💻</title>
    <link>https://www.prakashbhandari.com.np/tags/gcp/</link>
    <description>Recent content in GCP on Prakash&#39;s Blog 👨‍💻</description>
    <generator>Hugo -- 0.125.0</generator>
    <language>en</language>
    <lastBuildDate>Tue, 18 Feb 2025 16:20:01 +1100</lastBuildDate>
    <atom:link href="https://www.prakashbhandari.com.np/tags/gcp/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Supervised Fine-Tuning Large Language Models (LLMs) With Vertex AI</title>
      <link>https://www.prakashbhandari.com.np/posts/supervised-fine-tuning-large-language-models-vertex-ai/</link>
      <pubDate>Sun, 15 Sep 2024 21:05:53 +1000</pubDate>
      <guid>https://www.prakashbhandari.com.np/posts/supervised-fine-tuning-large-language-models-vertex-ai/</guid>
      <description>Fine-tuning a large language model (LLM) is the process of further training a pre-trained model to perform a specific task or work with a particular dataset. The dataset is often smaller and more specialized (e.g., sentiment analysis, medical language processing). So that the model can perform specific tasks with greater precision and accuracy.</description>
    </item>
    <item>
      <title>Large Multimodal Model(LMM) Prompting With Google Gemini and Vertex AI</title>
      <link>https://www.prakashbhandari.com.np/posts/large-multimodal-model-prompting-with-google-gemini/</link>
      <pubDate>Sat, 07 Sep 2024 17:26:54 +1000</pubDate>
      <guid>https://www.prakashbhandari.com.np/posts/large-multimodal-model-prompting-with-google-gemini/</guid>
      <description>A Large Multimodal Model (LMM) is an Artificial Intelligence (AI) model capable of processing and understanding multiple types of data modalities (such as text, audio, video, images, and potentially others) simultaneously, and providing outputs based on this information</description>
    </item>
  </channel>
</rss>
