PEFT How to use voidful/llmcodec-librispeech-abl-sa with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("voidful/llm-codec-abl-sa")
model = PeftModel.from_pretrained(base_model, "voidful/llmcodec-librispeech-abl-sa") 
