Update app.py

adding generation prompt while applying chat template

app.py

@@ -55,7 +55,7 @@ def generate(
     # if not message.strip():
     #     return "It looks like your message is empty. How can I assist you today?"
 
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt = 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.")