Skip to content

Instantly share code, notes, and snippets.

@sarony
Created October 23, 2023 05:49
Show Gist options
  • Save sarony/b7bc7cfaa785d39e5b3a3ca5fb38c1b9 to your computer and use it in GitHub Desktop.
Save sarony/b7bc7cfaa785d39e5b3a3ca5fb38c1b9 to your computer and use it in GitHub Desktop.
styling lists final part 1
<ul>
<li class="mb-8 border-b-2 border-gray pb-8">
<h2 class="font-bold">
temperature
</h2>
<p class="text-gray-500">
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
</p>
<p class="text-gray-500">
We generally recommend altering this or top_p but not both.
</p>
</li>
<li class="mb-8 border-b-2 border-gray pb-8">
<h2 class="font-bold">
top_p
</h2>
<p class="text-gray-500">
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
</p>
<p class="text-gray-500">
We generally recommend altering this or temperature but not both.
</p>
</li>
<li class="mb-4">
<h2 class="font-bold">
user
</h2>
<p class="text-gray-500">
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. <a href="#">Learn more</a>.
</p>
</li>
</ul>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment