Update app.py

app.py

@@ -61,9 +61,12 @@ chat_model = chat_model.to(device)  # type: ignore
 cls_model = cls_model.to(device)
 
 def generate_responses(model, tokenizer, prompts):
-    messages = [[{"role": "user", "content": message}] for message in prompts]
+    texts = []
+    for prompt in prompts:
+        message = [{"role": "user", "content": prompt}]
+        text = tokenizer.apply_chat_template(message, tokenize=False, add_generation_prompt=True)
+        texts.append(text)
 
-    texts = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
     print(texts[0])
 
     model_inputs = tokenizer(texts, padding=True, truncation=True, max_length=512, return_tensors="pt").to(model.device)