Update app.py

app.py

@@ -31,30 +31,19 @@ if device == "cuda":
         torch_dtype=torch.float16,
         device_map="auto",
     )
-    model = PeftModel.from_pretrained(
-        model, LORA_WEIGHTS, torch_dtype=torch.float16, force_download=True
-    )
+   
 elif device == "mps":
     model = LlamaForCausalLM.from_pretrained(
         BASE_MODEL,
         device_map={"": device},
         torch_dtype=torch.float16,
     )
-    model = PeftModel.from_pretrained(
-        model,
-        LORA_WEIGHTS,
-        device_map={"": device},
-        torch_dtype=torch.float16,
-    )
+   
 else:
     model = LlamaForCausalLM.from_pretrained(
         BASE_MODEL, device_map={"": device}, low_cpu_mem_usage=True
     )
-    model = PeftModel.from_pretrained(
-        model,
-        LORA_WEIGHTS,
-        device_map={"": device},
-    )
+    
 
 
 def generate_prompt(instruction, input=None):