Update app.py

app.py

@@ -43,7 +43,7 @@ def bot_streaming(message, history, max_new_tokens=250):
         messages.append({"role": "user", "content": [{"type": "text", "text": txt}]})
 
     stream = client.chat.completions.create(
-        model="meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
+        model="meta-llama/Llama-Vision-Free",
         messages=messages,
         max_tokens=max_new_tokens,
         stream=True,
@@ -58,14 +58,7 @@ def bot_streaming(message, history, max_new_tokens=250):
 
 demo = gr.ChatInterface(
     fn=bot_streaming,
-    title="Multimodal Llama",
-    examples=[
-        [{"text": "Which era does this piece belong to? Give details about the era.", "files":["./examples/rococo.jpg"]}, 200],
-        [{"text": "Where do the droughts happen according to this diagram?", "files":["./examples/weather_events.png"]}, 250],
-        [{"text": "What happens when you take out white cat from this chain?", "files":["./examples/ai2d_test.jpg"]}, 250],
-        [{"text": "Which company was this invoice addressed to?", "files":["./examples/invoice.png"]}, 250],
-        [{"text": "Where to find this monument? Can you give me other recommendations around the area?", "files":["./examples/wat_arun.jpg"]}, 250],
-    ],
+    title="Meta Llama 3.2 Vision 11B",
     textbox=gr.MultimodalTextbox(),
     additional_inputs=[
         gr.Slider(
@@ -77,7 +70,7 @@ demo = gr.ChatInterface(
         )
     ],
     cache_examples=False,
-    description="Try Multimodal Llama by Meta with the Together API in this demo. Upload an image, and start chatting about it, or simply try one of the examples below.",
+    description="Try Multimodal Llama by Meta with the Together API in this demo. Upload an image, and start chatting about it",
     stop_btn="Stop Generation",
     fill_height=True,
     multimodal=True