Update app.py

app.py

@@ -32,8 +32,8 @@ bnb_config = BitsAndBytesConfig(
 )
 
 tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-7b1")
-model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-7b1", device_map="auto")
-print(f"Successfully loaded the model into memory")
+model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-7b1")
+print(f"Successfully loaded the model")
 
 
 # Define stopping criteria. We do not use it for bloom model family but it can be used for llama model family