Update app.py

app.py

@@ -4,14 +4,13 @@ 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")
+hf_token = os.getenv("HF_TOKEN")
+login(token=hf_token)
 
 model_id = "meta-llama/Llama-3.2-1B"  # small enough to run locally on CPU
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id, token=hf_token)
+model = AutoModelForCausalLM.from_pretrained(model_id, token=hf_token)
 
 
 def chat(prompt):