Update app.py

app.py

@@ -2,8 +2,7 @@
 # warnings.filterwarnings("ignore")
 import gradio as gr
 import torch
-torch.set_num_threads()
-torch.set_num_interop_threads()
+torch.set_num_threads(1)
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from typing import Optional, Union, List, Dict, Any
 import random
@@ -133,6 +132,7 @@ model = AutoModelForCausalLM.from_pretrained(
     offload_folder="./", 
     low_cpu_mem_usage=True,
 )
+model=torch.compile(model)
 tokenizer = AutoTokenizer.from_pretrained("facebook/xglm-7.5B")