<?xml version="1.0" encoding="utf-8"?>
<?xml-stylesheet type="text/xsl" href="https://www.mindfiretechnology.com/blog/rss/xslt"?>
<rss xmlns:a10="http://www.w3.org/2005/Atom" version="2.0">
  <channel>
    <title>Mindfire Technology</title>
    <link>https://www.mindfiretechnology.com/blog/</link>
    <description>Welcome to our blog, where we share technical and business knowledge based on real life experiences.</description>
    <generator>Articulate, blogging built on Umbraco</generator>
    <item>
      <guid isPermaLink="false">2373</guid>
      <link>https://www.mindfiretechnology.com/blog/archive/lm-studio-the-easiest-way-to-get-started-with-hugging-face-llms/</link>
      <category>System.String[]</category>
      <title>LM Studio - The Easiest Way to get Started with Hugging Face LLMs</title>
      <description>&lt;p&gt;Want to get started with a local Hugging Face Large Language Model (LLM) but aren’t technical enough to just starting writing code?&lt;/p&gt;
&lt;p&gt;No worries! There is a particularly easy way to get started with local Hugging Face LLMs without needing to write a line of code. Just download LM Studio!&lt;/p&gt;
&lt;p&gt;&lt;a href="https://lmstudio.ai/"&gt;https://lmstudio.ai/&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;&lt;img src="https://www.mindfiretechnology.com/blog/media/lmstudio_picture1.png" alt="A screenshot of the LM Studio downloads page." /&gt;&lt;/p&gt;
&lt;p&gt;Now download the correct version for your Operating System. If you are a Windows shop like us, then select this button:&lt;/p&gt;
&lt;p&gt;&lt;img src="https://www.mindfiretechnology.com/blog/media/lmstudio_picture2.png" alt="LM Studio downloads page, zoomed in on the three downloads options. The top option is for MAC, the second is for Windows, and the third is for Linux in beta. The Windows option is circled." /&gt;&lt;/p&gt;
&lt;p&gt;Or whichever is appropriate for you.&lt;/p&gt;
&lt;p&gt;The tool itself is quite easy to use:&lt;/p&gt;
&lt;p&gt;&lt;img src="https://www.mindfiretechnology.com/blog/media/lmstudio_picture3.png" alt="The first page of the LM Studio tool, which has a search bar and a news column. In the search bar is written gpt4." /&gt;&lt;/p&gt;
&lt;p&gt;Now select the little magnifying glass to find a model off of the Hugging Face hub:&lt;/p&gt;
&lt;p&gt;&lt;img src="https://www.mindfiretechnology.com/blog/media/lmstudio_picture4.png" alt="The magnifying glass icon on the top left of the tool's interface is circled (second icon down). The page it presents has the search bar, wherein gpt4 is written. It has been searched and results showcase various gpt4 related models pulled from the Hugging Face hub." /&gt;&lt;/p&gt;
&lt;p&gt;For fun, search for ‘Story’ and press Go: (Or a good alternative is Mistral Instruct)&lt;/p&gt;
&lt;p&gt;&lt;img src="https://www.mindfiretechnology.com/blog/media/lmstudio_picture5.png" alt="The same page as before, only the search option of story is used and the results showcase various items/models with the keyword story." /&gt;&lt;/p&gt;
&lt;p&gt;Now go to the ‘Chat’ (the little dialogue bubble) and select the model you just downloaded:&lt;/p&gt;
&lt;p&gt;&lt;img src="https://www.mindfiretechnology.com/blog/media/lmstudio_picture6.png" alt="The question or statement cloud icon, located right under the magnifying glass icon near the top left, is circled. The subsequent page is shown showcasing the model that was previously downloaded. The model's name is located at the top and is circled &amp;quot;TheBloke mistral instruct v0 1 7B Q4_0 gguf&amp;quot;" /&gt;&lt;/p&gt;
&lt;p&gt;Once it is loaded, you can chat with your own private model.&lt;/p&gt;
&lt;p&gt;There are hundreds of models to play with on the Hugging Face hub!&lt;/p&gt;
&lt;p&gt;Why might you want to download a local LLM? One obvious reason is that Open AI’s ChatGPT and Google’s Gemini are both costly when used via an API. So, learning to play with a local LLM might make sense. Another reason might be that you want to circumvent the sometimes overly protective ‘safety rails’ they put on their LLMs. Or maybe you need a finetuned LLM for a specific purpose. Hugging Face has an amazing array of those. &lt;/p&gt;
&lt;p&gt;But whatever your reason, welcome to the wide world of Hugging Face LLMs!&lt;/p&gt;
&lt;p&gt;If you would like to learn more about Hugging Face, be sure to check out other other article on how to get started with Hugging Face and its' pipelines!&lt;/p&gt;
&lt;p&gt;&lt;a href="https://www.mindfiretechnology.com/blog/archive/an-introduction-to-hugging-face-and-their-pipelines/"&gt;https://www.mindfiretechnology.com/blog/archive/an-introduction-to-hugging-face-and-their-pipelines/&lt;/a&gt;&lt;/p&gt;
</description>
      <pubDate>Tue, 23 Apr 2024 09:00:00 -0600</pubDate>
      <a10:updated>2024-04-23T09:00:00-06:00</a10:updated>
    </item>
    <item>
      <guid isPermaLink="false">1642</guid>
      <link>https://www.mindfiretechnology.com/blog/archive/an-introduction-to-mocking-frameworks/</link>
      <category>System.String[]</category>
      <title>An Introduction to Mocking Frameworks</title>
      <description>&lt;h2&gt;Introduction&lt;/h2&gt;
&lt;p&gt;A mocking framework is used to create replacement objects. These objects can be Fakes, Stubs, and Mocks. In unit testing scenarios, developers use mocking frameworks to isolate dependencies. This allows for a quick, concise, and reliable way to ensure that the testing goes smoothly.&lt;/p&gt;
&lt;h2&gt;More Background on Using Mocking Frameworks&lt;/h2&gt;
&lt;p&gt;Like discussed above, mock frameworks are extensions testing techniques for object oriented programming. So what problem does it solve? Let’s find out.&lt;/p&gt;
&lt;p&gt;Say that you are testing your code that is still in development. In order to achieve the right results, you need to test its interactions with system resources, outside applications, and other dependencies. Unfortunately, you learn early on that that is not possible. Utilizing a mock framework allows for realistic emulations of the required interactions. &lt;/p&gt;
&lt;h2&gt;Creating a Mock&lt;/h2&gt;
&lt;p&gt;When you are running a test, they have to be set up. Oftentimes, dependencies are still under development and can require a set response, ie., a specific time of day, or error code. Even when you feel good that the code is interacting with external program or different system components, the tests can cannot be counted on.&lt;/p&gt;
&lt;p&gt;With mock, they interact with the code as interfaces, meaning that you must write a fully-interface compliant test. When this is done properly, the code will not be able to tell the difference between the mock and the actual object.&lt;/p&gt;
&lt;p&gt;Need a visual? Check out this Pluralsight video on how to Create mock objects with .NET&lt;/p&gt;
&lt;iframe width="560" height="315" src="https://www.youtube.com/embed/jDsekDhoGYc?ecver=1" frameborder="0" allowfullscreen&gt;&lt;/iframe&gt;
&lt;p&gt;So, should you start mocking frameworks for testing? The answer to that is totally up to you. It matters what you are testing and how in depth of an interaction you are looking to get. Mindfire Technology loves looking at different ways to make writing and testing code more efficiently. &lt;a href="https://www.mindfiretechnology.com/contact-us"&gt;Ask us what cool new tech we are working on, and we will answer!&lt;/a&gt;&lt;/p&gt;
</description>
      <pubDate>Fri, 05 May 2017 15:52:45 -0600</pubDate>
      <a10:updated>2017-05-05T15:52:45-06:00</a10:updated>
    </item>
  </channel>
</rss>