fix bug

app.py

@@ -61,7 +61,7 @@ def generate_for_examples(
     conversation = []
     conversation.append({"role": "user", "content": f"Translate the following text to {tgt_lang}: {message}"})
 
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt", add_generation_prompt=True)
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
     input_ids = input_ids.to(model.device)
@@ -94,7 +94,7 @@ def generate(
     conversation = []
     conversation.append({"role": "user", "content": f"Translate the following text to {tgt_lang}: {message}"})
 
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt", add_generation_prompt=True)
     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.")