Update app.py

app.py

@@ -6,7 +6,7 @@ from transformers import GenerationConfig, LlamaForCausalLM, LlamaTokenizer
 from transformers import Trainer
 
 BASE_MODEL = "TheBloke/stable-vicuna-13B-HF"
-model = LlamaForCausalLM.from_pretrained(BASE_MODEL, load_in_8bit=True, torch_dtype=torch.float16, device_map="auto")
+model = LlamaForCausalLM.from_pretrained(BASE_MODEL, load_in_8bit=True, torch_dtype=torch.float16, device_map="auto", offload_folder="./cache")
 tokenizer = LlamaTokenizer.from_pretrained(BASE_MODEL)
 tokenizer.pad_token_id = 0
 tokenizer.padding_side = "left"