How to use spjabech/llama_twitch_combined_jynxzi_v1_4bit_qlora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("gradientai/Llama-3-8B-Instruct-262k") model = PeftModel.from_pretrained(base_model, "spjabech/llama_twitch_combined_jynxzi_v1_4bit_qlora")
How to fix it?
