engineering/uncloseai.com
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

plausible & remarkbox comments

Browse source 
modified:   index.html
This commit is contained in:
root 2024-10-15 00:40:59 +00:00
parent a5d4bb88e0
commit f38be0ed01
1 changed files with 70 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

75
index.html
View file

@ -3,13 +3,14 @@
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Using Hermes AI - Free AI Service</title>
<title>Using Free Hermes AI Service | ai.unturf.com</title>
<style>
body {
font-family: Arial, sans-serif;
line-height: 1.6;
margin: 20px;
padding: 20px;
margin: 40px auto;
padding: 40px;
max-width: 960px;
background-color: #f4f4f4;
}
h1, h2, h3 {
@ -27,13 +28,15 @@
overflow-x: auto;
}
</style>
</head>
<body>
<h1>Welcome to ai.unturf.com</h1>
<p>At <strong>ai.unturf.com</strong>, we offer a free AI service powered by the model <strong>NousResearch/Hermes-3-Llama-3.1-8B</strong>. Our mission is to provide accessible AI tools for everyone, embodying the principles of free beer and free freedom. You can interact with our model without any cost, and you are encouraged to contribute and build upon our open-source framework.</p>
<p>At <strong>ai.unturf.com</strong>, we offer a free AI service powered by the model <a href="https://nousresearch.com/hermes3/" target="_blank">NousResearch/Hermes-3-Llama-3.1-8B</a>. Our mission is to provide accessible AI tools for everyone, embodying the principles of both free as in beer & free as in freedom. You can interact with our model without any cost, and you are encouraged to contribute and build upon the open-source code & models that we use.</p>
<h2>Using the Hermes AI Model</h2>
<p>This guide explains how to use the official OpenAI client to interact with the Hermes AI model hosted at <a href="https://hermes.ai.unturf.com/v1">hermes.ai.unturf.com/v1</a>. You can use this endpoint without an API key.</p>
<p>This guide explains how to use the official OpenAI client to interact with the Hermes AI model hosted at <strong>hermes.ai.unturf.com/v1</strong>. You can use this endpoint without an API key.</p>
<h3>Installing the OpenAI Client</h3>
<h4>Python</h4>
@ -104,6 +107,7 @@ for chunk in response:
# The 'ChatCompletionChunk' object exposes the 'choices' attribute directly
if hasattr(chunk.choices[0].delta, "content"):
print(chunk.choices[0].delta.content, end="")
</code></pre>
<h2>Node.js Example</h2>
@ -135,6 +139,7 @@ async function getResponse() {
}
getResponse();
</code></pre>
<h3>Streaming</h3>
@ -171,8 +176,68 @@ async function streamResponse() {
}
streamResponse();
</code></pre>
<p>Feel free to modify the <code>messages</code> array to ask different questions or adjust the <code>temperature</code> and <code>max_tokens</code> parameters according to your needs. Happy querying!</p>
<h2>How we run inference if you wanted to try to contribute</h2>
<p>We use vLLM to run models, currently full f16 safetensors. We make sure to use a virtualenv to hold the dependencies.</p>
<p>We are considering supporting ollama for better quant support.</p>
<pre><code>
cd ~
python3 -m venv env
source env/bin/activate
pip install vllm
python -m vllm.entrypoints.openai.api_server --model NousResearch/Hermes-3-Llama-3.1-8B --host 0.0.0.0 --port 18888 --max-model-len 16000
</code></pre>
<h2>Questions, Comments, Discussions</h2>
<!-- Remarkbox - Your readers want to communicate with you -->
<div id="remarkbox-div">
<noscript>
<iframe id=remarkbox-iframe src="https://my.remarkbox.com/embed?nojs=true" style="height:600px;width:100%;border:none!important" tabindex=0></iframe>
</noscript>
</div>
<script src="https://my.remarkbox.com/static/js/iframe-resizer/iframeResizer.min.js"></script>
<script>
var rb_owner_key = "220c5187-8a8d-11ef-a06a-29ab4fb285a0";
var thread_uri = window.location.href;
var thread_title = window.document.title;
var thread_fragment = window.location.hash;
// rb owner was here.
var rb_src = "https://my.remarkbox.com/embed" +
"?rb_owner_key=" + rb_owner_key +
"&thread_title=" + encodeURI(thread_title) +
"&thread_uri=" + encodeURIComponent(thread_uri) +
thread_fragment;
function create_remarkbox_iframe() {
var ifrm = document.createElement("iframe");
ifrm.setAttribute("id", "remarkbox-iframe");
ifrm.setAttribute("scrolling", "no");
ifrm.setAttribute("src", rb_src);
ifrm.setAttribute("frameborder", "0");
ifrm.setAttribute("tabindex", "0");
ifrm.setAttribute("title", "Remarkbox");
ifrm.style.width = "100%";
document.getElementById("remarkbox-div").appendChild(ifrm);
}
create_remarkbox_iframe();
iFrameResize(
{
checkOrigin: ["https://my.remarkbox.com"],
inPageLinks: true,
initCallback: function(e) {e.iFrameResizer.moveToAnchor(thread_fragment)}
},
document.getElementById("remarkbox-iframe")
);
</script>
<script defer data-domain="ai.unturf.com" src="https://analytics.unturf.com/js/script.js"></script>
</body>
</html>