Update app.py

app.py

@@ -6,6 +6,15 @@ model_name = "meta-llama/Llama-3.2-1B"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 
+# Fetch API token from environment
+api_token = os.getenv("Llama_Token")
+
+# Authenticate
+login(api_token)
+
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=api_token)
+model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=api_token)
+
 # Define the inference function
 def generate_text(prompt, max_length=100, temperature=0.7):
     inputs = tokenizer(prompt, return_tensors="pt")