Update app.py

app.py

@@ -85,4 +85,20 @@ with gr.Blocks(title=title) as demo:
     prompt.submit(fn=run, inputs=[prompt, mode, latency], outputs=[output])
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860, share=False)
+    demo.launch(server_name="0.0.0.0", server_port=7860, share=False)
+    from transformers import AutoModelForCausalLM, AutoTokenizer
+import gradio as gr
+
+
+model_id = "x402_hyperlayer_model"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+def chat(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=100)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+demo = gr.Interface(fn=chat, inputs="text", outputs="text", title="X402 HyperLayer Model")
+demo.launch()