<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Derrick Mwiti on Medium]]></title>
        <description><![CDATA[Stories by Derrick Mwiti on Medium]]></description>
        <link>https://medium.com/@mwitiderrick?source=rss-4b814c3bfc04------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*5NRYtO3VI-azBxs91N5x3Q.jpeg</url>
            <title>Stories by Derrick Mwiti on Medium</title>
            <link>https://medium.com/@mwitiderrick?source=rss-4b814c3bfc04------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sun, 15 Nov 2026 05:56:13 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@mwitiderrick/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[How to deal with rejection when you start writing]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/swlh/how-to-deal-with-rejection-when-you-start-writing-14248e71651d?source=rss-4b814c3bfc04------2"><img src="https://cdn-images-1.medium.com/max/2600/0*FP8YBuYJNxVANnOO" width="6000"></a></p><p class="medium-feed-snippet">and how to move on</p><p class="medium-feed-link"><a href="https://medium.com/swlh/how-to-deal-with-rejection-when-you-start-writing-14248e71651d?source=rss-4b814c3bfc04------2">Continue reading on The Startup »</a></p></div>]]></description>
            <link>https://medium.com/swlh/how-to-deal-with-rejection-when-you-start-writing-14248e71651d?source=rss-4b814c3bfc04------2</link>
            <guid isPermaLink="false">https://medium.com/p/14248e71651d</guid>
            <category><![CDATA[writing-tips]]></category>
            <category><![CDATA[writing]]></category>
            <dc:creator><![CDATA[Derrick Mwiti]]></dc:creator>
            <pubDate>Thu, 31 Oct 2024 14:37:55 GMT</pubDate>
            <atom:updated>2024-10-31T15:21:21.875Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[The Rise of AI Scams]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/the-rise-of-ai-scams-7400e1160380?source=rss-4b814c3bfc04------2"><img src="https://cdn-images-1.medium.com/max/2600/0*xcUtHexC71laX586" width="6000"></a></p><p class="medium-feed-snippet">You won&#x2019;t believe this&#x200A;&#x2014;&#x200A;these companies promised the future of AI, but instead delivered scams. And people lost millions. This article&#x2026;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/the-rise-of-ai-scams-7400e1160380?source=rss-4b814c3bfc04------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/the-rise-of-ai-scams-7400e1160380?source=rss-4b814c3bfc04------2</link>
            <guid isPermaLink="false">https://medium.com/p/7400e1160380</guid>
            <category><![CDATA[ai-scam]]></category>
            <category><![CDATA[ai]]></category>
            <dc:creator><![CDATA[Derrick Mwiti]]></dc:creator>
            <pubDate>Wed, 30 Oct 2024 00:01:57 GMT</pubDate>
            <atom:updated>2024-10-31T08:39:59.751Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[The State of AI Report 2024]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/the-state-of-ai-report-2024-15c0beeb8f80?source=rss-4b814c3bfc04------2"><img src="https://cdn-images-1.medium.com/max/2600/0*C9Ep564gq_mU5LqU" width="3840"></a></p><p class="medium-feed-snippet">The &#x201C;State of AI Report 2024&#x201D; just dropped. Here are the biggest highlights.</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/the-state-of-ai-report-2024-15c0beeb8f80?source=rss-4b814c3bfc04------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/the-state-of-ai-report-2024-15c0beeb8f80?source=rss-4b814c3bfc04------2</link>
            <guid isPermaLink="false">https://medium.com/p/15c0beeb8f80</guid>
            <category><![CDATA[ai]]></category>
            <dc:creator><![CDATA[Derrick Mwiti]]></dc:creator>
            <pubDate>Tue, 29 Oct 2024 20:01:55 GMT</pubDate>
            <atom:updated>2024-10-31T08:40:49.366Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Retrieval Augmented Generation]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/retrieval-augmented-generation-dcf155f92acd?source=rss-4b814c3bfc04------2"><img src="https://cdn-images-1.medium.com/max/2600/0*yqtoleOxCwfcPyq5" width="4928"></a></p><p class="medium-feed-snippet">Retrieving documents from external sources gives language models access to data that they didn&#x2019;t see during training. Particularly for&#x2026;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/retrieval-augmented-generation-dcf155f92acd?source=rss-4b814c3bfc04------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/retrieval-augmented-generation-dcf155f92acd?source=rss-4b814c3bfc04------2</link>
            <guid isPermaLink="false">https://medium.com/p/dcf155f92acd</guid>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[llm]]></category>
            <dc:creator><![CDATA[Derrick Mwiti]]></dc:creator>
            <pubDate>Sun, 27 Oct 2024 18:02:13 GMT</pubDate>
            <atom:updated>2024-10-29T06:29:16.610Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[The Transformer Architecture]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/the-transformer-architecture-d35d77c2c6d4?source=rss-4b814c3bfc04------2"><img src="https://cdn-images-1.medium.com/max/2600/0*JeYMHmQXWunaErL4" width="5038"></a></p><p class="medium-feed-snippet">In 2017, Ashish Vaswani et al wrote a paper that would change the natural language processing (NLP) scene forever, and most recently even&#x2026;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/the-transformer-architecture-d35d77c2c6d4?source=rss-4b814c3bfc04------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/the-transformer-architecture-d35d77c2c6d4?source=rss-4b814c3bfc04------2</link>
            <guid isPermaLink="false">https://medium.com/p/d35d77c2c6d4</guid>
            <category><![CDATA[deep-learning]]></category>
            <dc:creator><![CDATA[Derrick Mwiti]]></dc:creator>
            <pubDate>Fri, 25 Oct 2024 23:01:44 GMT</pubDate>
            <atom:updated>2024-10-29T06:29:36.646Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Llama Dive]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/llama-dive-def6de5c8629?source=rss-4b814c3bfc04------2"><img src="https://cdn-images-1.medium.com/max/2600/0*3US5F7fXF_MlhfdN" width="2842"></a></p><p class="medium-feed-snippet">It&#x2019;s no doubt that generative AI will change every industry. The current state of generative AI, particularly text-to-image generation and&#x2026;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/llama-dive-def6de5c8629?source=rss-4b814c3bfc04------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/llama-dive-def6de5c8629?source=rss-4b814c3bfc04------2</link>
            <guid isPermaLink="false">https://medium.com/p/def6de5c8629</guid>
            <category><![CDATA[deep-learning]]></category>
            <dc:creator><![CDATA[Derrick Mwiti]]></dc:creator>
            <pubDate>Fri, 25 Oct 2024 21:02:13 GMT</pubDate>
            <atom:updated>2024-10-29T06:29:57.137Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Large Language Model Evaluation Metrics]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/large-language-model-evaluation-metrics-fcf7ff666765?source=rss-4b814c3bfc04------2"><img src="https://cdn-images-1.medium.com/max/2600/0*4Peo0dOJXjKkQqKG" width="5184"></a></p><p class="medium-feed-snippet">The most common evaluating metrics for large language models are:</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/large-language-model-evaluation-metrics-fcf7ff666765?source=rss-4b814c3bfc04------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/large-language-model-evaluation-metrics-fcf7ff666765?source=rss-4b814c3bfc04------2</link>
            <guid isPermaLink="false">https://medium.com/p/fcf7ff666765</guid>
            <category><![CDATA[machine-learning]]></category>
            <dc:creator><![CDATA[Derrick Mwiti]]></dc:creator>
            <pubDate>Fri, 25 Oct 2024 17:02:13 GMT</pubDate>
            <atom:updated>2024-10-29T06:30:43.301Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[How to Fine-Tune Llama 2 With LoRA]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/how-to-fine-tune-llama-2-with-lora-284ad8345346?source=rss-4b814c3bfc04------2"><img src="https://cdn-images-1.medium.com/max/2600/0*-JFlTTlB2vWUGBFH" width="4000"></a></p><p class="medium-feed-snippet">Until recently, fine-tuning large language models (LLMs) on a single GPU was a pipe dream. This is because of the large size of these&#x2026;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/how-to-fine-tune-llama-2-with-lora-284ad8345346?source=rss-4b814c3bfc04------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/how-to-fine-tune-llama-2-with-lora-284ad8345346?source=rss-4b814c3bfc04------2</link>
            <guid isPermaLink="false">https://medium.com/p/284ad8345346</guid>
            <dc:creator><![CDATA[Derrick Mwiti]]></dc:creator>
            <pubDate>Tue, 22 Oct 2024 21:23:40 GMT</pubDate>
            <atom:updated>2024-10-29T06:31:09.965Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[GPT Instruction Fine-tuning With Keras]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/gpt-instruction-fine-tuning-with-keras-b3c370eb5b77?source=rss-4b814c3bfc04------2"><img src="https://cdn-images-1.medium.com/max/1280/0*E9pw9TXiw-xsAt3E.png" width="1280"></a></p><p class="medium-feed-snippet">Fine-tuning has become the new training because training large language models (LLMs) from scratch is computationally expensive. It also&#x2026;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/gpt-instruction-fine-tuning-with-keras-b3c370eb5b77?source=rss-4b814c3bfc04------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/gpt-instruction-fine-tuning-with-keras-b3c370eb5b77?source=rss-4b814c3bfc04------2</link>
            <guid isPermaLink="false">https://medium.com/p/b3c370eb5b77</guid>
            <category><![CDATA[deep-learning]]></category>
            <dc:creator><![CDATA[Derrick Mwiti]]></dc:creator>
            <pubDate>Mon, 15 Jan 2024 06:13:06 GMT</pubDate>
            <atom:updated>2024-10-29T06:31:41.856Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Convolutional Neural Networks in JAX: Ultimate Guide]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/convolutional-neural-networks-in-jax-ultimate-guide-f421053d50ad?source=rss-4b814c3bfc04------2"><img src="https://cdn-images-1.medium.com/max/1280/0*Z9wJjVm5qHeHmXgq.png" width="1280"></a></p><p class="medium-feed-snippet">JAX is a high performance library that offers accelerated computing through XLA and Just In Time Compilation. It also has handy features&#x2026;</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/convolutional-neural-networks-in-jax-ultimate-guide-f421053d50ad?source=rss-4b814c3bfc04------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/convolutional-neural-networks-in-jax-ultimate-guide-f421053d50ad?source=rss-4b814c3bfc04------2</link>
            <guid isPermaLink="false">https://medium.com/p/f421053d50ad</guid>
            <category><![CDATA[jax]]></category>
            <category><![CDATA[deep-learning]]></category>
            <dc:creator><![CDATA[Derrick Mwiti]]></dc:creator>
            <pubDate>Tue, 19 Dec 2023 06:46:42 GMT</pubDate>
            <atom:updated>2024-10-29T06:32:03.770Z</atom:updated>
        </item>
    </channel>
</rss>