Create app.py

app.py

@@ -0,0 +1,18 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+import spaces
+
+client = InferenceClient("meta-llama/Meta-Llama-3-70B-Instruct")
+messages=[]
+client.chat_completion(messages, max_tokens=1024)
+
+@spaces.GPU()
+def respond(prompt):
+    response = client.chat_completion(
+        model="meta-llama/Meta-Llama-3-70B-Instruct",
+        messages=messages,
+        max_tokens=500,
+    )
+    return response.content
+
+gr.ChatInterface(respond).launch()