Update app.py

app.py

@@ -70,7 +70,7 @@ def bot_streaming(message, history, together_api_key, max_new_tokens=250, temper
 
     try:
         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,
             temperature=temperature,
@@ -79,9 +79,8 @@ def bot_streaming(message, history, together_api_key, max_new_tokens=250, temper
 
         response = ""
         for chunk in stream:
-            if chunk.choices and chunk.choices[0].delta and chunk.choices[0].delta.content is not None:
-                response += chunk.choices[0].delta.content
-                yield response
+            response += chunk.choices[0].delta.content or ""
+            yield response
 
         if not response:
             yield "No response generated. Please try again."
@@ -92,7 +91,6 @@ def bot_streaming(message, history, together_api_key, max_new_tokens=250, temper
         else:
             yield f"An error occurred: {str(e)}"
 
-# The rest of your Gradio interface code remains the same
 with gr.Blocks() as demo:
     gr.Markdown("# Meta Llama-3.2-11B-Vision-Instruct (FREE)")
     gr.Markdown("Try the new Llama 3.2 11B Vision API by Meta for free through Together AI. Upload an image, and start chatting about it. Just paste in your Together AI API key and get started!")