Update app.py

app.py

@@ -1,11 +1,20 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+# Use a pipeline as a high-level helper
+from transformers import pipeline
 
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+pipe = pipeline("text-generation", model="Qwen/Qwen2.5-7B")
+pipe(messages)
 """
 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")
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B")
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B")
 
 def respond(
     message,