import torch
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer, pipeline
 
peft_model_id = "./code-llama-7b-text-to-sql"
# peft_model_id = args.output_dir
 
# Load Model with PEFT adapter
model = AutoPeftModelForCausalLM.from_pretrained(
  peft_model_id,
  device_map="auto",
  torch_dtype=torch.float16
)
tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
# load into pipeline
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)