Update app.py

app.py

@@ -1,10 +1,10 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from together import Together
 
 """
 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 = Together()
 
 
 def respond(
@@ -27,7 +27,8 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
+    for message in client.chat.completions.create(
+        model="meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
         messages,
         max_tokens=max_tokens,
         stream=True,