Update app.py

app.py

@@ -3,6 +3,7 @@
 
 import os
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig, pipeline
+from transformers import LlamaTokenizer
 import streamlit as st
 import torch
 
@@ -17,7 +18,8 @@ st.title("Experimental KPhi3 Model - Currently in Training")
 # Load tokenizer and model
 @st.cache_resource(show_spinner="Loading model...")
 def load_model(repo_name):
-    tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
+    # tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
+    tokenizer = LlamaTokenizer.from_pretrained(repo_name, trust_remote_code=True)
     generator_conf = GenerationConfig.from_pretrained(repo_name)
     model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True, torch_dtype=torch.bfloat16)
     return tokenizer, generator_conf, model