Update app.py

app.py

@@ -1,3 +1,4 @@
+import spaces
 import gradio as gr
 import transformers
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
@@ -9,7 +10,7 @@ import threading
 
 model_id = "PhysicsWallahAI/Aryabhata-1.0"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id).to('cuda')
 
 def process_questions(example):
     example["question_text"] = example["question"]
@@ -37,6 +38,7 @@ def strip_bad_tokens(s, stop_strings):
             return s[:-len(suffix)]
     return s
 
+@spaces.GPU
 def generate_answer_stream(question):
     messages = [
         {'role': 'system', 'content': 'Think step-by-step; put only the final answer inside \\boxed{}.'},