Update for ZeroGPU

app.py

@@ -2,6 +2,7 @@ from threading import Thread
 from typing import Iterator
 
 import gradio as gr
+import spaces
 import torch
 from transformers import (
     AutoConfig,
@@ -49,6 +50,7 @@ if torch.cuda.is_available():
     tokenizer.use_default_system_prompt = False
 
 
+@spaces.GPU
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],

requirements.txt

@@ -4,5 +4,6 @@ gradio==3.47.1
 protobuf==3.20.3
 scipy==1.11.2
 sentencepiece==0.1.99
-torch==2.0.1
+spaces==0.16.1
+torch==2.0.0
 transformers==4.34.0