为荷兰语打造的对话模型，基于Mistral 7B改进并提升对话质量。
GEITje 7B Ultra: A Conversational Model for Dutch
- 在自建合成对话数据上进行监督微调，增强荷兰语对话能力。
- 通过合成反馈数据进行偏好对齐，提升模型回应的自然度。
- 开源模型与数据集，适合荷兰语NLP研究者使用。
语言模型快速发展，但主要聚焦英语，常忽视其他语言的充分预训练。这导致需通过微调将英语主导模型适配至其他语境。针对荷兰语，此前已有基于Mistral 7B的『GEITje』模型。本文在此基础上，利用新创建的高质量合成对话数据集进行监督微调，并在合成反馈数据集上执行额外的偏好对齐。所开发的模型与构建的数据集均公开可用。
原文摘要 · Abstract (English)
Language models have rapidly evolved, predominantly focusing on English while often neglecting extensive pretraining in other languages. This approach has required initiatives to adapt powerful, English-centric models to other linguistic contexts through finetuning. For Dutch, such a recent endeavour is ``GEITje'' a model originally derived from the English-based Mistral 7B. Building on this fundamental work, the current research extends the capabilities of GEITje by supervised finetuning on newly created high-quality synthetic conversational datasets, along with an additional preference alignment procedure on a synthetic feedback dataset. Both the developed models and the created datasets are openly available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。