How to use 9sub/llama3_10epoch_no_quantize 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, "9sub/llama3_10epoch_no_quantize")
9sub commited on 