Update app.py

app.py

@@ -5,9 +5,9 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 from transformers import pipeline
 
-pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True)
+#pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True)
 
-#client = InferenceClient("microsoft/Phi-3-mini-128k-instruct")
+client = InferenceClient("microsoft/Phi-3-mini-128k-instruct")
 
 
 @spaces.GPU