Update app.py

app.py

@@ -4,8 +4,10 @@ from huggingface_hub import InferenceClient
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
+client = InferenceClient(
+    base_url="https://huggingface.co/api/integrations/dgx/v1"
+    # api_key="..."  # Uncomment and use your actual API key here if required
+)
 
 def respond(
     message,
@@ -29,6 +31,7 @@ def respond(
 
     for message in client.chat_completion(
         messages,
+        model="meta-llama/Meta-Llama-3.1-8B-Instruct",
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,