Update app.py

app.py

@@ -3,6 +3,7 @@ import torch
 from transformers import pipeline
 import os
 import spaces
+import functools
 
 #load_dotenv()
 key=os.environ["HF_KEY"]
@@ -24,8 +25,8 @@ print("[INFO] load model ...")
 pipe=load_model()
 print("[INFO] model loaded")
 
+# Remove the @gr.cache decorator since it's not available
 @spaces.GPU
-@gr.cache(persist=True)  # Add persistent caching
 def predict(text):
     outputs = pipe(text)
     scores= [x["score"] for x in outputs]
@@ -52,7 +53,7 @@ with gr.Blocks() as demo:
             gr.Examples(
                 examples=["العاصمة د <mask> هي الرباط","المغرب <mask> زوين","انا سميتي مريم، و كنسكن ف<mask> العاصمة دفلسطين"],
                 inputs=input_text,
-                cache_examples=True,
+                cache_examples=True
                 preprocess=True  # Precompute examples
             )
         
@@ -60,7 +61,7 @@ with gr.Blocks() as demo:
             # Output probabilities
             output_labels = gr.Label(
                 label="Prediction Results",
-                show_label=False,
+                show_label=False
                 num_top_classes=5  # Limit to top 5 predictions
             )
 
@@ -79,4 +80,4 @@ with gr.Blocks() as demo:
 
 # Launch the app with queue
 demo.queue(concurrency_count=3)  # Allow 3 concurrent predictions
-demo.launch(show_api=False)  # Disable API tab if not needed
+demo.launch()  # Remove show_api parameter if it causes issues