Update app.py

app.py

@@ -1,16 +1,20 @@
+import os
 from flask import Flask, request, jsonify
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
+hf_token = os.getenv("HF_TOKEN")
+
 MODEL_ID = "Qwen/Qwen2.5-Coder-1.0B-Instruct"
 
 print("Loading tokenizer...")
-tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, token=hf_token )
 
 print("Loading model...")
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
-    device_map="cpu"
+    device_map="cpu",
+    token=hf_token 
 )
 print("Model loaded successfully")