Update app.py

app.py

@@ -14,6 +14,12 @@ tokenizer = AutoTokenizer.from_pretrained("Navid-AI/Yehia-7B-preview", token=os.
 model = AutoModelForCausalLM.from_pretrained("Navid-AI/Yehia-7B-preview", torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2", token=os.getenv("HF_TOKEN")).to(device)
 streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 
+HEADER = """<div style="text-align: center; margin-bottom: 20px;">
+    <h1>Yehia 7B Preview</h1>
+    <p style="font-size: 16px; color: #888;">How far can GRPO get you ?</p>
+</div>
+"""
+
 @spaces.GPU
 def respond(
     message,
@@ -44,8 +50,7 @@ def respond(
         response += new_text
         yield response
 
-
-demo = gr.ChatInterface(
+chat_interface = gr.ChatInterface(
     respond,
     textbox=gr.Textbox(text_align="right", rtl=True, submit_btn=True, stop_btn=True),
     additional_inputs=[
@@ -55,7 +60,7 @@ demo = gr.ChatInterface(
         gr.Slider(minimum=0.0, maximum=1.0, value=0.6, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.0, maximum=2.0, value=1.1, step=0.05, label="Repetition penalty"),
     ],
-    example_labels=[["من الذى أكل الجبنة ؟"]],
+    examples=[["من الذى أكل الجبنة ؟"]],
     example_icons=[["💡"]],
     cache_examples=False,
     # head="<h1 style='text-align:center;'>Yehia 7B Preview</h1>",
@@ -69,6 +74,9 @@ demo = gr.ChatInterface(
     theme="JohnSmith9982/small_and_pretty",
 )
 
+with gr.Blocks(fill_height=True) as demo:
+    gr.HTML(HEADER)
+    chat_interface.render()
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.queue().launch(ssr_mode=False)