Update app.py

app.py

@@ -13,10 +13,11 @@ subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENT
 
 model_id = "microsoft/Phi-3-mini-128k-instruct"
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",
+    trust_remote_code=True,
     attn_implementation="flash_attention_2"
 )