Update app.py

app.py

@@ -47,7 +47,8 @@ def load_model_norm():
     # To use a different branch, change revision
     # For example: revision="main"
     model = AutoModelForCausalLM.from_pretrained(model_name_or_path,device_map="auto", trust_remote_code=True,revision="gptq-4bit-128g-actorder_True")
-
+    # Switch to CPU inference
+    model.cpu()
     tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
     return model, tokenizer