format

index.html

@@ -47,7 +47,19 @@ SweetSpot v2 — Energy-per-Token demo
 </h2>
 
 <p>
-Interactive visualization of the analytical energy model. Load any dense LLM from huggingface! 
+This interactive demo visualizes our analytical model for predicting the  <b>energy consumption per generated token</b> as a function of the number of output tokens (<i>n</i><sub>out</sub>). 
+Select one of the validated models used in the paper or load the architecture of any <b>dense decoder-only Transformer</b> (up to approximately 20B parameters) from Hugging Face to explore how the different terms contribute to the prediction.
+</p>
+
+<p>
+The model was fitted using empirical measurements collected on an <b>NVIDIA H100 GPU</b> with <b>NVIDIA TensorRT-LLM</b> (<code>max_batch_size = 1024</code>, <code>max_num_tokens = 8192</code>). Future releases will extend the analysis to additional hardware platforms and inference frameworks.
+</p>
+
+<p>
+For the complete methodology, experimental validation, and citation information, please see the paper:
+<a href="YOUR_PAPER_URL" target="_blank">
+SweetSpot v2: Analytical Modeling of LLM Energy Consumption
+</a>.
 </p>
 
 
@@ -56,27 +68,27 @@ Interactive visualization of the analytical energy model. Load any dense LLM fro
 <div class="row">
 
 <div>
-<label>d (hidden size)</label>
+<label>Hidden size (d):</label>
 <input id="d" type="number" value="4096">
 </div>
 
 <div>
-<label>L (layers)</label>
+<label>Layers (L):</label>
 <input id="L" type="number" value="36">
 </div>
 
 <div>
-<label>nq (query heads)</label>
+<label>Query heads (<i>n</i><sub>q</sub>):</label>
 <input id="nq" type="number" value="64">
 </div>
 
 <div>
-<label>nkv (KV heads)</label>
+<label>KV heads (<i>n</i><sub>kv</sub>):</label>
 <input id="nkv" type="number" value="64">
 </div>
 
 <div>
-<label>Input tokens</label>
+<label>Input Tokens (<i>n</i><sub>in</sub>):</label>
 <input id="nin" type="number" value="64">
 </div>