How to use gdevakumar/llama_3_1_8B_DPO with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/meta-llama-3.1-8b-instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "gdevakumar/llama_3_1_8B_DPO")
https://huggingface.co/gdevakumar/llama_3_1_8B_DPO/resolve/main/tokenizer.json
hf download hf://gdevakumar/llama_3_1_8B_DPO/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/gdevakumar/llama_3_1_8B_DPO/resolve/main/tokenizer.json
