How to use seize/Llama-seize-JEJU-Ko-3-8B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("MLP-KTLim/llama-3-Korean-Bllossom-8B") model = PeftModel.from_pretrained(base_model, "seize/Llama-seize-JEJU-Ko-3-8B")
