Update app.py

app.py

@@ -2,21 +2,14 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 from llama_cpp import Llama
 
-llm = Llama.from_pretrained(
-	repo_id="bartowski/Reasoning-Llama-1b-v0.1-GGUF",
-	filename="Reasoning-Llama-1b-v0.1-f16.gguf",
-)
+# Initialize the InferenceClient
+client = InferenceClient()
 
-llm.create_chat_completion(
-	messages = [
-		{
-			"role": "user",
-			"content": "What is the capital of France?"
-		}
-	]
+llm = Llama.from_pretrained(
+    repo_id="bartowski/Reasoning-Llama-1b-v0.1-GGUF",
+    filename="Reasoning-Llama-1b-v0.1-f16.gguf",
 )
 
-
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -37,6 +30,7 @@ def respond(
 
     response = ""
 
+    # Use the client to get the chat completion
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -44,15 +38,10 @@ def respond(
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
-
+        token = message['choices'][0]['delta']['content']
         response += token
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -69,6 +58,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()