How to use QinLiuNLP/llama3-sudo with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B") model = PeftModel.from_pretrained(base_model, "QinLiuNLP/llama3-sudo")
https://huggingface.co/QinLiuNLP/llama3-sudo/resolve/main/tokenizer.json
hf download hf://QinLiuNLP/llama3-sudo/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/QinLiuNLP/llama3-sudo/resolve/main/tokenizer.json
