zerogpu

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+import spaces
 import torch
 
 from transformers import AutoTokenizer, AutoModelForCausalLM
@@ -11,6 +12,7 @@ print("Downloading model")
 tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
 model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename, torch_dtype=torch_dtype)
 
+@spaces.GPU
 def greet(name):
     return "Hello " + name + "!!"