Update app.py

app.py

@@ -9,6 +9,7 @@ import torch
 REPO_NAME = 'schuler/experimental-JP47D21-KPhi-3-micro-4k-instruct'
 
 # How to cache?
+@spaces.GPU()
 def load_model(repo_name):
     tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
     generator_conf = GenerationConfig.from_pretrained(repo_name)
@@ -20,10 +21,12 @@ tokenizer, generator_conf, model = load_model(REPO_NAME)
 
 global_error = ''
 try:
+    @spaces.GPU()
     generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
 except Exception as e:
     global_error =  f"Failed to load model: {str(e)}"
 
+@spaces.GPU()
 def respond(
     message,
     history: list[tuple[str, str]],