Update app.py

app.py

@@ -1,10 +1,20 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from llama_cpp import Llama
 
-"""
-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")
+llm = Llama.from_pretrained(
+	repo_id="bartowski/Reasoning-Llama-1b-v0.1-GGUF",
+	filename="Reasoning-Llama-1b-v0.1-f16.gguf",
+)
+
+llm.create_chat_completion(
+	messages = [
+		{
+			"role": "user",
+			"content": "What is the capital of France?"
+		}
+	]
+)
 
 
 def respond(