Update app.py

app.py

@@ -4,7 +4,7 @@ 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("unsloth/Llama-3.2-11B-Vision-Instruct")
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
 def respond(
@@ -30,7 +30,7 @@ def respond(
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
-        stream=True,
+        stream=False,
         temperature=temperature,
         top_p=top_p,
     ):