Update app.py

app.py

@@ -30,7 +30,7 @@ streamer = TextStreamer(tokenizer)
 #model = AutoModelForCausalLM.from_pretrained(model, trust_remote_code=True, token = access_token, device_map="cuda", load_in_8bit=True, offload_folder="offload/")
 #model = PeftModel.from_pretrained(model, peft_model, offload_folder="offload/")
 
-model = AutoModelForCausalLM.from_pretrained(model, trust_remote_code=True, device_map="cuda", load_in_4bit=True)
+model = AutoModelForCausalLM.from_pretrained(model, trust_remote_code=True, device_map="cuda")
 model = PeftModel.from_pretrained(model, peft_model)
 
 device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')