Update app.py

app.py

@@ -37,7 +37,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_name = "microsoft/Phi-3.5-mini-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.int8, device_map="auto")
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
 
 print("Start the model init process")
 """model = model = GPT4All(model_name, model_path, allow_download = False, device="cpu")