trust_remote_code=True

app.py

@@ -8,8 +8,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_name = "microsoft/Phi-3-mini-128k-instruct"
 
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, trust_remote_code=True)
 
 pipeline = transformers.pipeline(
     "text-generation",