Update app.py

app.py

@@ -20,6 +20,7 @@ tokenizer = AutoTokenizer.from_pretrained(
 model = LlavaQwen2ForCausalLM.from_pretrained(
     'qnguyen3/nanoLLaVA',
     torch_dtype=torch.float16,
+    attn_implementation="flash_attention_2",
     trust_remote_code=True)
 
 model.to('cuda')
@@ -118,7 +119,7 @@ def bot_streaming(message, history):
       yield generated_text_without_prompt
 
 
-demo = gr.ChatInterface(fn=bot_streaming, title="nanoLLaVA", examples=[{"text": "What is on the flower?", "files":["./bee.jpg"]},
+demo = gr.ChatInterface(fn=bot_streaming, title="🚀nanoLLaVA", examples=[{"text": "What is on the flower?", "files":["./bee.jpg"]},
                                                                       {"text": "How to make this pastry?", "files":["./baklava.png"]}], 
                         description="Try [nanoLLaVA](https://huggingface.co/qnguyen3/nanoLLaVA) in this demo. Built on top of [Quyen-SE-v0.1](https://huggingface.co/vilm/Quyen-SE-v0.1) (Qwen1.5-0.5B) and [Google SigLIP-400M](https://huggingface.co/google/siglip-so400m-patch14-384). Upload an image and start chatting about it, or simply try one of the examples below. If you don't upload an image, you will receive an error.",
                         stop_btn="Stop Generation", multimodal=True)