Update app.py

app.py

@@ -17,9 +17,10 @@ offload_folder = './model_weights'
 if not os.path.exists(offload_folder):
     os.makedirs(offload_folder)
 
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map='auto')
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False,)
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 model = model.to(torch.bfloat16)
+model = model.to(device_map='auto', offload_folder=offload_folder)
 
 class OrcaChatBot:
     def __init__(self, model, tokenizer, system_message="You are Orca, an AI language model created by Microsoft. You are a cautious assistant. You carefully follow instructions. You are helpful and harmless and you follow ethical guidelines and promote positive behavior."):