Update app.py

app.py

@@ -17,12 +17,11 @@ else:
 
 model = LlamaForCausalLM.from_pretrained(
     "decapoda-research/llama-7b-hf",
-    load_in_8bit=True,
     torch_dtype=torch.float16,
     device_map="auto",
 )
 model = PeftModel.from_pretrained(
-    model, "tloen/alpaca-lora-7b", torch_dtype=torch.float16
+    model, "tloen/alpaca-lora-7b", torch_dtype=torch.float16, force_download=True
 )