Update app.py

app.py

@@ -10,20 +10,7 @@ from unsloth import FastLanguageModel
 import torch
 import re
 
-# Load the model
-max_seq_length = 2048
-dtype = None
-load_in_4bit = True
-
-model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name="unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
-    max_seq_length=max_seq_length,
-    dtype=dtype,
-    load_in_4bit=load_in_4bit,
-)
 
-# Enable native 2x faster inference
-FastLanguageModel.for_inference(model)
 
 # Define helper functions
 async def fetch_data(url):
@@ -115,7 +102,24 @@ def translate_text(text):
         print(f"An error occurred during translation: {e}")
         return None
 
+@spaces.GPU()
 def summarize_url(url):
+
+    # Load the model
+    max_seq_length = 2048
+    dtype = None
+    load_in_4bit = True
+    
+    model, tokenizer = FastLanguageModel.from_pretrained(
+        model_name="unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+        max_seq_length=max_seq_length,
+        dtype=dtype,
+        load_in_4bit=load_in_4bit,
+    )
+    
+    # Enable native 2x faster inference
+    FastLanguageModel.for_inference(model)
+    
     result = asyncio.run(fetch_data(url))
     text = concatenate_text(result)
     translated_text = translate_text(text)