Update app.py

app.py

@@ -5,7 +5,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 from transformers import pipeline
 
-pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-128k-instruct", torch_dtype=torch.bfloat16, device_map="auto")
+pipe = pipeline("text-generation", model="microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True)
 
 #client = InferenceClient("microsoft/Phi-3-mini-128k-instruct")