import torch
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer
 
peft_model_id = "./llama-3-70b-hf-no-robot"
 
# Load Model with PEFT adapter
model = AutoPeftModelForCausalLM.from_pretrained(
  peft_model_id,
  torch_dtype=torch.float16,
  quantization_config= {"load_in_4bit": True},
  device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(peft_model_id)