Update app.py

app.py

@@ -1,3 +1,21 @@
 import gradio as gr
 
-gr.load("models/Qwen/Qwen2.5-Coder-32B-Instruct").launch()
+#gr.load("models/Qwen/Qwen2.5-Coder-32B-Instruct").launch()
+from huggingface_hub import InferenceClient
+
+client = InferenceClient(api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")
+
+messages = [
+	{
+		"role": "user",
+		"content": "What is the capital of France?"
+	}
+]
+
+completion = client.chat.completions.create(
+    model="Qwen/Qwen2.5-Coder-32B-Instruct", 
+	messages=messages, 
+	max_tokens=500
+)
+
+print(completion.choices[0].message)