from peft import PeftModel
from transformers import LLaMATokenizer, LLaMAForCausalLM, GenerationConfig

tokenizer = LLaMATokenizer.from_pretrained("decapoda-research/llama-7b-hf")
model = LLaMAForCausalLM.from_pretrained(
    "decapoda-research/llama-7b-hf",
    load_in_8bit=True,
    device_map="auto",
)
model = PeftModel.from_pretrained(model, "tloen/alpaca-lora-7b")