How to use lewtun/dpo-model-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct") model = PeftModel.from_pretrained(base_model, "lewtun/dpo-model-lora")
https://huggingface.co/lewtun/dpo-model-lora/resolve/main/tokenizer.json
hf download hf://lewtun/dpo-model-lora/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/lewtun/dpo-model-lora/resolve/main/tokenizer.json
