aaaaa

app.py

@@ -5,7 +5,7 @@ from transformers import pipeline
 
 # Inference client setup
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-# pipe = pipeline("text-generation", "microsoft/Phi-3-mini-4k-instruct", torch_dtype=torch.bfloat16, device_map="auto")
+pipe = pipeline("text-generation", "microsoft/Phi-3-mini-4k-instruct", torch_dtype=torch.bfloat16, device_map="auto")
 
 # Global flag to handle cancellation
 stop_inference = False