How to use BetterHF/llama3.1-8b-instruct-hqa-sft-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/data/huggingface_models/Meta-Llama-3.1-8B-Instruct") model = PeftModel.from_pretrained(base_model, "BetterHF/llama3.1-8b-instruct-hqa-sft-lora")
https://huggingface.co/BetterHF/llama3.1-8b-instruct-hqa-sft-lora/resolve/main/training_loss.png
hf download hf://BetterHF/llama3.1-8b-instruct-hqa-sft-lora/training_loss.png
curl -L -o training_loss.png https://huggingface.co/BetterHF/llama3.1-8b-instruct-hqa-sft-lora/resolve/main/training_loss.png
