PEFT How to use kernelguardian/llama2action with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("TinyPixel/Llama-2-7B-bf16-sharded")
model = PeftModel.from_pretrained(base_model, "kernelguardian/llama2action") 
