Update app.py

app.py

@@ -61,7 +61,7 @@ def generate(
         )
     conversation.append({"role": "user", "content": message})
 
-    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt")
+    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True,add_special_tokens = True, return_tensors="pt")
     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.")