Changes to tokenspeed.scroll.pub

root

24 days ago

Initial commit

body.html

Changed around line 1
+ 
+   Token Speed Calculator
+   Estimate GPT model performance based on vocabulary size and GPU memory
+ 
+ 
+ 
+   
+     
+       Vocabulary Size:
+       
+     
+ 
+     
+       GPU Memory (GB):
+       
+     
+ 
+     
+ 
+     
+       Performance Estimates
+       
+         132,000 Token Vocabulary
+         Tokens per second: -
+       
+       
+         2 Token Vocabulary
+         Tokens per second: -
+       
+     
+   
+ 
+   
+     How It Works
+     The calculator estimates token processing speed based on:
+     
+       Vocabulary size impact on model complexity
+       GPU memory capacity for model operations
+       Typical performance characteristics of 7B parameter models
+     
+   
+ 
+ 
+ 
+   Disclaimer: Results are estimates based on typical model performance characteristics.
+ 

index.scroll

Changed around line 1
+ buildHtml
+ baseUrl https://tokenspeed.scroll.pub
+ metaTags
+ editButton /edit.html
+ title Token Speed Calculator
+ style.css
+ body.html
+ script.js

prompt.json

Changed around line 1
+ {
+   "id": "579879b9-4258-49b8-8f99-220ade8029b4",
+   "object": "chat.completion",
+   "created": 1735383272,
+   "model": "deepseek-chat",
+   "choices": [
+     {
+       "index": 0,
+       "message": {
+         "role": "assistant",
+         "content": "---domain---\ntokenspeed.scroll.pub\n---index.scroll---\nbuildHtml\nbaseUrl https://tokenspeed.scroll.pub\nmetaTags\neditButton /edit.html\ntitle Token Speed Calculator\nstyle.css\nbody.html\nscript.js\n---body.html---\n\n  Token Speed Calculator\n  Estimate GPT model performance based on vocabulary size and GPU memory
\n\n\n\n  \n    \n      Vocabulary Size:\n      \n    
\n    \n    \n      GPU Memory (GB):\n      \n    
\n\n    \n\n    \n      Performance Estimates\n      \n        132,000 Token Vocabulary\n        Tokens per second: -
\n      
\n      \n        2 Token Vocabulary\n        Tokens per second: -
\n      
\n    
\n  \n\n  \n    How It Works\n    The calculator estimates token processing speed based on:
\n    \n      Vocabulary size impact on model complexity
\n      GPU memory capacity for model operations
\n      Typical performance characteristics of 7B parameter models
\n    \n  \n\n\n\n  Disclaimer: Results are estimates based on typical model performance characteristics.
\n\n---style.css---\n:root {\n  --primary: #2563eb;\n  --primary-hover: #1d4ed8;\n  --background: #f8fafc;\n  --text: #1e293b;\n  --card-bg: #ffffff;\n  --shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.1);\n}\n\n* {\n  margin: 0;\n  padding: 0;\n  box-sizing: border-box;\n}\n\nbody {\n  font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;\n  background-color: var(--background);\n  color: var(--text);\n  line-height: 1.6;\n  padding: 2rem;\n}\n\nheader {\n  text-align: center;\n  margin-bottom: 3rem;\n}\n\nh1 {\n  font-size: 2.5rem;\n  color: var(--primary);\n  margin-bottom: 0.5rem;\n}\n\n.calculator {\n  max-width: 800px;\n  margin: 0 auto;\n  background: var(--card-bg);\n  padding: 2rem;\n  border-radius: 0.5rem;\n  box-shadow: var(--shadow);\n}\n\n.input-group {\n  margin-bottom: 1.5rem;\n}\n\nlabel {\n  display: block;\n  margin-bottom: 0.5rem;\n  font-weight: 500;\n}\n\ninput {\n  width: 100%;\n  padding: 0.75rem;\n  border: 1px solid #e2e8f0;\n  border-radius: 0.375rem;\n  font-size: 1rem;\n}\n\nbutton {\n  width: 100%;\n  padding: 0.75rem;\n  background-color: var(--primary);\n  color: white;\n  border: none;\n  border-radius: 0.375rem;\n  font-size: 1rem;\n  cursor: pointer;\n  transition: background-color 0.2s;\n}\n\nbutton:hover {\n  background-color: var(--primary-hover);\n}\n\n.results {\n  margin-top: 2rem;\n}\n\n.result-card {\n  background: var(--card-bg);\n  padding: 1.5rem;\n  margin: 1rem 0;\n  border-radius: 0.375rem;\n  box-shadow: var(--shadow);\n}\n\n.result-card h3 {\n  color: var(--primary);\n  margin-bottom: 0.5rem;\n}\n\n.explanation {\n  max-width: 800px;\n  margin: 3rem auto;\n  padding: 2rem;\n  background: var(--card-bg);\n  border-radius: 0.5rem;\n  box-shadow: var(--shadow);\n}\n\nfooter {\n  text-align: center;\n  margin-top: 3rem;\n  color: #64748b;\n}\n\n@media (max-width: 768px) {\n  body {\n    padding: 1rem;\n  }\n  \n  h1 {\n    font-size: 2rem;\n  }\n  \n  .calculator, .explanation {\n    padding: 1rem;\n  }\n}\n---script.js---\ndocument.getElementById('calculate-btn').addEventListener('click', function() {\n  const vocabSize = parseInt(document.getElementById('vocab-size').value);\n  const gpuMemory = parseInt(document.getElementById('gpu-memory').value);\n\n  if (isNaN(vocabSize) || isNaN(gpuMemory)) {\n    alert('Please enter valid numbers for both fields');\n    return;\n  }\n\n  // Performance estimation formulas\n  const baseSpeed = (gpuMemory / 24) * 50; // Base speed at 24GB\n  const largeVocabFactor = Math.max(0.1, 1 - (vocabSize / 132000));\n  const smallVocabFactor = Math.min(2, 2 - (vocabSize / 2));\n\n  const largeVocabSpeed = Math.round(baseSpeed * largeVocabFactor);\n  const smallVocabSpeed = Math.round(baseSpeed * smallVocabFactor);\n\n  document.getElementById('result-large').textContent = largeVocabSpeed;\n  document.getElementById('result-small').textContent = smallVocabSpeed;\n});\n---end---"
+       },
+       "logprobs": null,
+       "finish_reason": "stop"
+     }
+   ],
+   "usage": {
+     "prompt_tokens": 280,
+     "completion_tokens": 1364,
+     "total_tokens": 1644,
+     "prompt_cache_hit_tokens": 0,
+     "prompt_cache_miss_tokens": 280
+   },
+   "system_fingerprint": "fp_f1afce2943"
+ }

readme.scroll

Changed around line 1

+ # tokenspeed.scroll.pub

+ Website generated by DeepSeek from prompt: Calculate it for this a 7b parameters gpt model one with 132000 tokens vocab and one with 2 tokens vocab Give me actual calculations for example how many tokens per second it will output on 24 gigs GPU

script.js

Changed around line 1
+ document.getElementById('calculate-btn').addEventListener('click', function() {
+   const vocabSize = parseInt(document.getElementById('vocab-size').value);
+   const gpuMemory = parseInt(document.getElementById('gpu-memory').value);
+ 
+   if (isNaN(vocabSize) || isNaN(gpuMemory)) {
+     alert('Please enter valid numbers for both fields');
+     return;
+   }
+ 
+   // Performance estimation formulas
+   const baseSpeed = (gpuMemory / 24) * 50; // Base speed at 24GB
+   const largeVocabFactor = Math.max(0.1, 1 - (vocabSize / 132000));
+   const smallVocabFactor = Math.min(2, 2 - (vocabSize / 2));
+ 
+   const largeVocabSpeed = Math.round(baseSpeed * largeVocabFactor);
+   const smallVocabSpeed = Math.round(baseSpeed * smallVocabFactor);
+ 
+   document.getElementById('result-large').textContent = largeVocabSpeed;
+   document.getElementById('result-small').textContent = smallVocabSpeed;
+ });

style.css

Changed around line 1
+ :root {
+   --primary: #2563eb;
+   --primary-hover: #1d4ed8;
+   --background: #f8fafc;
+   --text: #1e293b;
+   --card-bg: #ffffff;
+   --shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.1);
+ }
+ 
+ * {
+   margin: 0;
+   padding: 0;
+   box-sizing: border-box;
+ }
+ 
+ body {
+   font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;
+   background-color: var(--background);
+   color: var(--text);
+   line-height: 1.6;
+   padding: 2rem;
+ }
+ 
+ header {
+   text-align: center;
+   margin-bottom: 3rem;
+ }
+ 
+ h1 {
+   font-size: 2.5rem;
+   color: var(--primary);
+   margin-bottom: 0.5rem;
+ }
+ 
+ .calculator {
+   max-width: 800px;
+   margin: 0 auto;
+   background: var(--card-bg);
+   padding: 2rem;
+   border-radius: 0.5rem;
+   box-shadow: var(--shadow);
+ }
+ 
+ .input-group {
+   margin-bottom: 1.5rem;
+ }
+ 
+ label {
+   display: block;
+   margin-bottom: 0.5rem;
+   font-weight: 500;
+ }
+ 
+ input {
+   width: 100%;
+   padding: 0.75rem;
+   border: 1px solid #e2e8f0;
+   border-radius: 0.375rem;
+   font-size: 1rem;
+ }
+ 
+ button {
+   width: 100%;
+   padding: 0.75rem;
+   background-color: var(--primary);
+   color: white;
+   border: none;
+   border-radius: 0.375rem;
+   font-size: 1rem;
+   cursor: pointer;
+   transition: background-color 0.2s;
+ }
+ 
+ button:hover {
+   background-color: var(--primary-hover);
+ }
+ 
+ .results {
+   margin-top: 2rem;
+ }
+ 
+ .result-card {
+   background: var(--card-bg);
+   padding: 1.5rem;
+   margin: 1rem 0;
+   border-radius: 0.375rem;
+   box-shadow: var(--shadow);
+ }
+ 
+ .result-card h3 {
+   color: var(--primary);
+   margin-bottom: 0.5rem;
+ }
+ 
+ .explanation {
+   max-width: 800px;
+   margin: 3rem auto;
+   padding: 2rem;
+   background: var(--card-bg);
+   border-radius: 0.5rem;
+   box-shadow: var(--shadow);
+ }
+ 
+ footer {
+   text-align: center;
+   margin-top: 3rem;
+   color: #64748b;
+ }
+ 
+ @media (max-width: 768px) {
+   body {
+     padding: 1rem;
+   }
+ 
+   h1 {
+     font-size: 2rem;
+   }
+ 
+   .calculator, .explanation {
+     padding: 1rem;
+   }
+ }