Update app.py

app.py

@@ -146,14 +146,20 @@ def chat(message, history):
       time.sleep(0.01)
       yield generated_text_without_prompt
 
-
-demo = gr.ChatInterface(
-    fn=chat,
-    description="""Try [Vintern-1B](https://huggingface.co/5CD-AI/Viet-InternVL2-1B) in this demo. Vintern 1B is a multimodal large language model series, featuring models of various sizes. For each size, we release instruction-tuned models optimized for multimodal tasks. Vintern-1B consists of [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px), an MLP projector, and [Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct).""",
-    examples=[{"text": "Mô tả hình ảnh.", "files":["./demo_3.jpg"]},
-              {"text": "Trích xuất các thông tin từ ảnh.", "files":["./demo_1.jpg"]}, 
-              {"text": "Mô tả hình ảnh một cách chi tiết.", "files":["./demo_2.jpg"]}],
-    title="❄️ Vintern-1B ❄️",
-    multimodal=True,
-)
+CSS ="""
+.contain { display: flex; flex-direction: column; }
+#component-0 { height: 100%; }
+#chatbot { flex-grow: 1; }
+"""
+
+with gr.Blocks(css=CSS) as demo:
+    chatbot = gr.ChatInterface(
+        fn=chat,
+        description="""Try [Vintern-1B](https://huggingface.co/5CD-AI/Viet-InternVL2-1B) in this demo. Vintern 1B is a multimodal large language model series, featuring models of various sizes. For each size, we release instruction-tuned models optimized for multimodal tasks. Vintern-1B consists of [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px), an MLP projector, and [Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct).""",
+        examples=[{"text": "Mô tả hình ảnh.", "files":["./demo_3.jpg"]},
+                  {"text": "Trích xuất các thông tin từ ảnh.", "files":["./demo_1.jpg"]}, 
+                  {"text": "Mô tả hình ảnh một cách chi tiết.", "files":["./demo_2.jpg"]}],
+        title="❄️ Vintern-1B ❄️",
+        multimodal=True,
+    )
 demo.queue().launch()