Update app.py

app.py

@@ -1,9 +1,16 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import spaces
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+from transformers import pipeline
 
-client = InferenceClient("microsoft/Phi-3-mini-128k-instruct")
+pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-128k-instruct", torch_dtype=torch.bfloat16, device_map="auto")
 
+#client = InferenceClient("microsoft/Phi-3-mini-128k-instruct")
 
+
+@spaces.GPU
 def respond(
     message,
     history: list[tuple[str, str]],