Update app.py

app.py

@@ -14,12 +14,17 @@ tokenizer.pad_token = tokenizer.eos_token
 model = AutoModelForCausalLM.from_pretrained(
     BASE_MODEL,
     torch_dtype=torch.float32,
+    offload_folder="offload",
     device_map={"": "cpu"},
     low_cpu_mem_usage=True
 )
 
 # Load LoRA
-model = PeftModel.from_pretrained(model, LORA_PATH)
+model = PeftModel.from_pretrained(
+    model,
+    LORA_PATH,
+    is_trainable=False
+)
 model.eval()