Update app.py

app.py

@@ -6,8 +6,12 @@ from transformers import TextStreamer
 
 import spaces
 
+quantization_config = BitsAndBytesConfig(
+    load_in_4bit=True, bnb_4bit_compute_dtype=torch.float16
+)
+
 # Load model and tokenizer
-model = AutoModelForCausalLM.from_pretrained("Rorical/0-roleplay", return_dict=True, trust_remote_code=True)
+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)
 tokenizer.chat_template = "{% for message in messages %}{{'' + ((message['role'] + '\n') if message['role'] != '' else '') + message['content'] + '' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '星野\n' }}{% endif %}"