import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

# Config
base_model_id = "meta-llama/Llama-3.1-8B-Instruct"
repo_id = "Jason-42195/VNU-SecAlign"
adapter_subfolder = "checkpoints/final_checkpoint"

# Initialize tokenizer
tokenizer = AutoTokenizer.from_pretrained(base_model_id)

# Load original model
model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    device_map="auto",
    trust_remote_code=True
)

# Load Adapter from subfolder 
model = PeftModel.from_pretrained(
    model,
    repo_id,
    subfolder=adapter_subfolder
)

model.eval()

Judge used in evaluation: GPT-4o (deployment gpt-4o, temperature=0.0).