Update app.py

app.py

@@ -1,6 +1,9 @@
 from fastapi import FastAPI
 import time
 import torch
+import os
+
+access_token = os.evn["read_access"]
 
 from transformers import AutoModelForCausalLM, AutoTokenizer
 device = "cpu" # the device to load the model onto
@@ -28,11 +31,12 @@ time5 = time.time()
 print(time5-time4)
 
 
-tokenizer2 = AutoTokenizer.from_pretrained("google/gemma-2-2b-it")
+tokenizer2 = AutoTokenizer.from_pretrained("google/gemma-2-2b-it", token=access_token)
 model2 = AutoModelForCausalLM.from_pretrained(
     "google/gemma-2-2b-it",
     device_map="auto",
     torch_dtype=torch.bfloat16,
+    token=access_token
 )