Update app.py

app.py

@@ -17,19 +17,6 @@ base_model = "https://huggingface.co/Shangding-Gu/Lunyu-LLM/"
 
 tokenizer = LlamaTokenizer.from_pretrained(base_model)
 load_8bit = False
-if device == "cuda":
-    model = LlamaForCausalLM.from_pretrained(
-            base_model,
-            load_in_8bit=load_8bit,
-            torch_dtype=torch.float16,
-            device_map="auto",
-        )
-elif device == "mps":
-    model = LlamaForCausalLM.from_pretrained(
-            base_model,
-            device_map={"": device},
-            torch_dtype=torch.float16,
-        )
 
 model.config.pad_token_id = tokenizer.pad_token_id = 0  # unk
 model.config.bos_token_id = 1