Update app.py

app.py

@@ -2,9 +2,7 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-# Load tokenizer and model
 model_id = "microsoft/Magma-8B"
-
 tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
@@ -12,14 +10,12 @@ model = AutoModelForCausalLM.from_pretrained(
     trust_remote_code=True
 )
 
-# Define a simple text-generation function
 def generate_response(prompt):
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
     with torch.no_grad():
         outputs = model.generate(**inputs, max_new_tokens=100)
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-# Create Gradio interface
 interface = gr.Interface(
     fn=generate_response,
     inputs=gr.Textbox(lines=2, placeholder="Enter your prompt here..."),
@@ -27,5 +23,4 @@ interface = gr.Interface(
     title="Magma-8B Text Generator"
 )
 
-# Launch the app (use launch instead of mount_gradio_app)
-interface.launch()
+interface.launch(share=False, enable_queue=True)