Update app.py

app.py

@@ -21,8 +21,8 @@ quantization_config = BitsAndBytesConfig(
 )
 
 # Load model and tokenizer
-model = AutoModelForCausalLM.from_pretrained("Rorical/0-roleplay", return_dict=True, trust_remote_code=True, quantization_config=quantization_config)
-tokenizer = AutoTokenizer.from_pretrained("Rorical/0-roleplay", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("Rorical/0-roleplay", return_dict=True, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("Rorical/0-roleplay", trust_remote_code=True, quantization_config=quantization_config)
 tokenizer.chat_template = "{% for message in messages %}{{'<|im_start|>' + ((message['role'] + ':\n') if message['role'] != '' else '') + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>星野:\n' }}{% endif %}" # Be careful that this model used custom chat template.
 
 # Define the response function