Update app.py

app.py

@@ -6,7 +6,15 @@ import os
 from time import time
 import pandas as pd
 
+import os
+from huggingface_hub import login
+
+HF_TOKEN = os.getenv("nex_model")  # Updated key name for clarity
+
+if not HF_TOKEN:
+    raise ValueError("Hugging Face token not found. Please set the 'NEX_MODEL' environment variable.")
 
+login(token=HF_TOKEN)
 # ==============================
 # Helper: Human-readable bytes
 def sizeof_fmt(num, suffix="B"):
@@ -87,13 +95,14 @@ def load_model_and_tokenizer(doc_text_count):
         model_name,
         device_map="auto",  # Automatically allocate model to devices
         quantization_config=quantization_config,
-        model_max_length=1.3*round(doc_text_count * 0.3 + 1)
+        model_max_length=1.3*round(doc_text_count * 0.3 + 1),
+        token=HF_TOKEN
     )
 
     # Load the tokenizer
     tokenizer = AutoTokenizer.from_pretrained(
         model_name
-        
+        ,token=HF_TOKEN
     )
     return tokenizer, model