Speak to me: How many words a model is reading
<p><a href="https://en.wikipedia.org/wiki/Large_language_model" rel="noopener ugc nofollow" target="_blank">LLMs</a> have shown their skills in recent months, demonstrating that they are proficient in a wide variety of tasks. All this through one mode of interaction: prompting.</p>
<p>In recent months there has been a rush to broaden the context of language models. <strong>But how does this affect a language model?</strong></p>
<p>This article is divided into different sections, for each section we will answer these questions:</p>
<ul>
<li>What is a prompt and how to build a good prompt?</li>
<li>What is the context window? How long it can be? What is limiting the length of the input sequence of a model? Why this is important?</li>
<li>How we can overcome these limitations?</li>
<li>Do the models use the long context window?</li>
</ul>
<h1>How to talk to a model?</h1>
<p><img alt="LLM context window" src="https://miro.medium.com/v2/resize:fit:700/0*JDksYRmh6HYO2A7h" style="height:467px; width:700px" /></p>
<p>Photo by <a href="https://unsplash.com/@jamietempleton?utm_source=medium&utm_medium=referral" rel="noopener ugc nofollow" target="_blank">Jamie Templeton</a> on <a href="https://unsplash.com/?utm_source=medium&utm_medium=referral" rel="noopener ugc nofollow" target="_blank">Unsplash</a></p>
<h2>What is a prompt and what is a good prompt?</h2>
<p>Simply put, a prompt is how one interacts with a <a href="https://en.wikipedia.org/wiki/Large_language_model" rel="noopener ugc nofollow" target="_blank">large language model</a> (LLM). Given an <a href="https://en.wikipedia.org/wiki/Large_language_model" rel="noopener ugc nofollow" target="_blank">LLM</a>, we can interact by providing instructions in text form. This textual prompt contains the information the model needs to process a response. The prompt can contain a question, task description, content, and lots of other information. Essentially, through the prompt we provide the model with what our intent is and what we expect it to respond to.</p>
<p><a href="https://towardsdatascience.com/speak-to-me-how-many-words-a-model-is-reading-331e3af86d27"><strong>Click Here</strong></a></p>