Update app.py

app.py

@@ -3,6 +3,11 @@ from huggingface_hub import InferenceClient
 
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+ht_token=os.getenv("HF_TOKEN")
 
 model_id = "meta-llama/Llama-3.2-1B"  # small enough to run locally on CPU
 tokenizer = AutoTokenizer.from_pretrained(model_id)