Update main.py

main.py

@@ -8,7 +8,7 @@ import torch
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 tokenizer = AutoTokenizer.from_pretrained("huggyllama/llama-7b")
-model = AutoModelForCausalLM.from_pretrained("huggyllama/llama-7b", device_map="auto", torch_dtype=torch.float16)
+model = AutoModelForCausalLM.from_pretrained("huggyllama/llama-7b", device_map="auto",offload_folder="offload", torch_dtype=torch.float16)
 
 #model = model.to(device)