Update app.py

app.py

@@ -6,7 +6,7 @@ from typing import Iterator
 import torch
 
 import gradio as gr
-import spaces
+# import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
@@ -16,11 +16,12 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192"))
 
 model_id = "BramVanroy/GEITje-7B-ultra"
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
+model = model.to("cuda" if torch.cuda.is_available() else "cpu")
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 tokenizer.pad_token_id = tokenizer.eos_token_id
 
 
-@spaces.GPU
+# @spaces.GPU
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],