Update app.py

app.py

@@ -111,7 +111,7 @@ from huggingface_hub import InferenceClient
 def llm_chat_response(text):
     HF_TOKEN = os.getenv("HF_TOKEN")
     client = InferenceClient(
-        provider="novita",  # Use the provider that supports conversational image-text tasks.
+        provider="cerebras",  # Use the provider that supports conversational image-text tasks.
         api_key=HF_TOKEN,
     )
     
@@ -127,7 +127,7 @@ def llm_chat_response(text):
     }]
     
     response_from_llama = client.chat.completions.create(
-        model="meta-llama/Llama-3.2-11B-Vision-Instruct",
+        model="meta-llama/Llama-4-Scout-17B-16E-Instruct",
         messages=messages,
         max_tokens=500,
     )