Update app.py

app.py

@@ -165,7 +165,7 @@ def llm_chat_response(text, image_base64=None):
         
         logger.info("Initializing InferenceClient...")
         client = InferenceClient(
-            provider="nebius",  # Using novita as in your working example
+            provider="cerebras",  # Using cerebras as in this example
             api_key=HF_TOKEN
         )
         
@@ -199,7 +199,7 @@ def llm_chat_response(text, image_base64=None):
         logger.info("Sending request to model...")
         try:
             completion = client.chat.completions.create(
-                model="mistralai/Mistral-Small-3.1-24B-Instruct-2503",
+                model="meta-llama/Llama-4-Scout-17B-16E-Instruct",
                 messages=messages,
                 max_tokens=500
             )