How to use rlabz/quantum_tts with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "rlabz/quantum_tts")
https://huggingface.co/rlabz/quantum_tts/resolve/main/tokenizer_config.json
hf download hf://rlabz/quantum_tts/tokenizer_config.json
curl -L -o tokenizer_config.json https://huggingface.co/rlabz/quantum_tts/resolve/main/tokenizer_config.json
