Update

app.py

@@ -5,7 +5,7 @@ from typing import Iterator
 import gradio as gr
 import spaces
 import torch
-from transformers import AutoModelForCausalLM, GemmaTokenizerFast, TextIteratorStreamer
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
 DESCRIPTION = """\
 # Gemma 2 2B IT
@@ -24,7 +24,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
 model_id = "google/gemma-2-2b-it"
-tokenizer = GemmaTokenizerFast.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",
@@ -34,7 +34,7 @@ model.config.sliding_window = 4096
 model.eval()
 
 
-@spaces.GPU(duration=90)
+@spaces.GPU
 def generate(
     message: str,
     chat_history: list[dict],