Update zero-shot-classification.html

zero-shot-classification.html

@@ -6,14 +6,12 @@
     <title>Zero Shot Classification - Hugging Face Transformers.js</title>
 
     <script type="module">
-        // To-Do: transformers.js 라이브러리 중 pipeline 함수를 import하십시오.
-         import { pipeline } from
-      'https://cdn.jsdelivr.net/npm/@xenova/transformers@2.5.4';
+        // Import the library
+        import { pipeline } from 'https://cdn.jsdelivr.net/npm/@xenova/transformers@2.5.4';
         // Make it available globally
         window.pipeline = pipeline;
     </script>
 
-  
     <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.1.0/dist/css/bootstrap.min.css" rel="stylesheet">
 
     <link rel="stylesheet" href="css/styles.css">
@@ -92,38 +90,25 @@
     </div>
 
     <script>
-
         let classifier;
         let classifierMulti;
-
         // Initialize the sentiment analysis model
         async function initializeModel() {
-          classifier = await pipeline('zero-shot-classification', 'Xenova/mobilebert-uncased-mnli');
-          classifierMulti = await pipeline('zero-shot-classification', 'Xenova/nli-deberta-v3-xsmall'); 
-          // To-Do: pipeline 함수에 task와 model을 지정하여 zero 샷 분류 모델을 생성하여 classifier에 저장하십시오. 모델은 Xenova/mobilebert-uncased-mnli 사용
-            // To-Do: pipeline 함수에 task와 model을 지정하여 zero 샷 분류 모델을 생성하여 classifierMulti에 저장하십시오. 모델은 Xenova/nli-deberta-v3-xsmall 사용
-            
-
+            classifier = await pipeline('zero-shot-classification', 'Xenova/mobilebert-uncased-mnli');
+            classifierMulti = await pipeline('zero-shot-classification', 'Xenova/nli-deberta-v3-xsmall');
         }
-
         async function classifyText() {
             const text = document.getElementById("textText").value.trim();
             const labels = document.getElementById("labelsText").value.trim().split(",").map(item => item.trim());
-
             const result = await classifier(text, labels);
-
             document.getElementById("outputArea").innerText = JSON.stringify(result, null, 2);
         }
-
         async function classifyTextMulti() {
             const text = document.getElementById("textTextMulti").value.trim();
             const labels = document.getElementById("labelsTextMulti").value.trim().split(",").map(item => item.trim());
-
             const result = await classifierMulti(text, labels, { multi_label: true });
-
             document.getElementById("outputAreaMulti").innerText = JSON.stringify(result, null, 2);
         }
-
         // Initialize the model after the DOM is completely loaded
         window.addEventListener("DOMContentLoaded", initializeModel);
     </script>