Update app.py

app.py

@@ -53,13 +53,12 @@ def generate_text(input_text):
         output = model.generate(input_ids, max_new_tokens=1, do_sample=True, temperature=1.0, top_p=0.3, top_k=0)
         new_word = tokenizer.decode(output[0][-1:], skip_special_tokens=True)
 
-        print(new_word, end="", flush=True)
+        print(new_word, end="", flush=True)  # Print to console for monitoring
         generated_text += new_word
 
-
         input_ids = output
 
-    return generated_text
+        yield generated_text  # Yield the updated text after each word
 
 # Create the Gradio interface
 iface = gr.Interface(
@@ -74,7 +73,7 @@ iface = gr.Interface(
 
 # For local testing:
 iface.launch(share=True)
-deploy()
+# deploy()
 
 
 # Hugging Face Spaces will automatically launch the interface.