Update app.py

app.py

@@ -1,15 +1,9 @@
-import os
 import gradio as gr
-import requests
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# Retrieve the API token from environment variables
-model_repo_id = os.getenv("MODEL_REPO_ID")
-if not model_repo_id:
-    raise ValueError("MODEL_REPO_ID token not found. Please set the MODEL_REPO_ID environment variable.")
-
-# Hugging Face Inference API Details
-API_URL = "https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-1B-Instruct"
-HEADERS = {"Authorization": f"Bearer {model_repo_id}"}
+# Load model directly
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
 
 
 def generate_exegesis(passage):