Update app.py

app.py

@@ -13,12 +13,11 @@ model = AutoModelForCausalLM.from_pretrained(
 
 generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
-# Define function for API
 def chat(prompt):
     output = generator(prompt, max_new_tokens=200, do_sample=True)
     return output[0]["generated_text"]
 
-# Gradio interface (can also work as API)
 demo = gr.Interface(fn=chat, inputs="text", outputs="text")
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch(share=True, server_name="0.0.0.0", server_port=7860, show_api=True)