Update app.py

app.py

@@ -70,14 +70,15 @@ def generate(
     if model == "A":
         model = modelA
         tokenizer = tokenizerA
-        enc = tokenizer(make_prompt(message), return_tensors="pt", padding=True, truncation=True)
-        input_ids = enc.input_ids.to(model.device)
+        
 
     else:
         model = modelB
         tokenizer = tokenizerB
-        input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
-        
+    
+    enc = tokenizer(make_prompt(message), return_tensors="pt", padding=True, truncation=True)
+    input_ids = enc.input_ids.to(model.device) 
+    
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")