This repo contains the model checkpoints for: — model family llama13b — optimized with the loss SFT+KTO — aligned using the SHP, Anthropic HH and Open Assistant datasets. To prompt Archangel models, ensure that the format is consistent with that of TuluV2. For example, a prompt should be formatted as follows, where corresponds to the human’s role and corresponds to the LLM’s role. The human should speak first: Note that a beginning-of-sequence (BOS) token is automatically added by all Archangel models during tokenization and does not have to be added by you. No end-of-sequence (EOS) token is added to the prompt. For models trained with our conditional SFT model, the tokenizers have additional tokens and included in the embeddings. To generate with these control tokens in the context, postpend either to the prompt. Please refer to our code repository or blog which contains intructions for training your own HALOs and links to our model cards. If you find this repo or the technical paper useful in your research, please feel free to cite our work:
Модальности:
Генерация текста
Задача: Генерация текста
Автор: ContextualAI
Теги: llama, human feedback, rlhf, preferences, alignment, HALO, halos, dpo
Лайков: 3 | Загрузок: 72
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
