PEFT How to use voidful/llmcodec-librispeech-no-init with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "voidful/llmcodec-librispeech-no-init") 
