A LoRA adapter that steers Helsinki-NLP/opus-mt-en-es toward literary prose. 589K trainable parameters — 0.75% of the model — trained on opus_books en-es. 19.99 sacreBLEU against 17.09 for the untouched base model. 2.4 MB; loads on top of the base with PEFT.
machine-translation seq2seq neural-machine-translation lora fine-tuning peft literary-translation marianmt machine-translation-evaluation helsinki-nlp lora-training english-to-spanish peft-fine-tuning-llm opus-books opus-mt sacrebleu peft-fine-tuning peft-llm peft-lora peft-qlora
-
Updated
Oct 25, 2026