SusGen-GPT-LLaMA3
Collection
5 items • Updated • 1
How to use WHATX/30k-Llama3-8B with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("../ckpts/Meta-Llama-3-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "WHATX/30k-Llama3-8B")The best checkpoint is 240-epoch.