Update app.py

app.py

@@ -2,6 +2,9 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
+import os
+
+HuggingFaceFineGrainedReadToken
 
 # Base model (LLaMA 3.1 8B) from Meta
 base_model_name = "meta-llama/Llama-3.1-8B"
@@ -9,6 +12,9 @@ base_model_name = "meta-llama/Llama-3.1-8B"
 # Your fine-tuned LoRA adapter (uploaded to Hugging Face)
 lora_model_name = "starnernj/Early-Christian-Church-Fathers-LLaMA-3.1-Fine-Tuned"
 
+# Login because LLaMA 3.1 8B is a gated model
+login(token=os.getenv("HuggingFaceFineGrainedReadToken"))
+
 # Load base model
 model = AutoModelForCausalLM.from_pretrained(base_model_name)