This repo provides the checkpoint of Qwen2.5-7B-LongPO-128K in our paper «LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization». — Self-evolving long-context alignment without human/superior LLMs annotations. — Extending context length while keeping aligned in one stage. — No degradation on short-context capabilities. * indicates an experimental version (for rebuttal purposes) that may have not been fully tuned or provided with sufficient data to achieve convergence. — Our results are evaluated with greedy decoding. — Baseline results marked with ᵇ are evaluated by us, while unmarked baseline results are sourced from their official report. If you find our project useful, hope you can star our repo and cite our paper as follows:
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: DAMO-NLP-SG
Теги: qwen2, conversational, text-generation-inference, endpoints_compatible
Лайков: 4 | Загрузок: 17
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
