We introduce CroissantLLM, a 1.3B language model pretrained on a set of 3T English and French tokens, to bring to the research and industrial community a high-performance, fully open-sourced bilingual model that runs swiftly on consumer-grade local hardware. To that end, we pioneer the approach of training an intrinsically bilingual model with a 1:1 English-to-French pretraining data ratio, a custom tokenizer, and bilingual finetuning datasets. We release the training dataset, notably containing a French split with manually curated, high-quality, and varied data sources. To assess performance outside of English, we craft a novel benchmark, FrenchBench, consisting of an array of classification and generation tasks, covering various orthogonal aspects of model performance in the French Language. Additionally, rooted in transparency and to foster further Large Language Model research, we release codebases, and dozens of checkpoints across various model sizes, training data distributions, and training steps, as well as fine-tuned Chat models, and strong translation models. We evaluate our model through the FMTI framework, and validate 81 % of the transparency criteria, far beyond the scores of even most open initiatives. This work enriches the NLP landscape, breaking away from previous English-centric work in order to strengthen our understanding of multilinguality in language models.

翻译：我们提出CroissantLLM——一个在3万亿英语和法语token上预训练的13亿参数语言模型，旨在为研究和工业界提供高性能、完全开源且能在消费级本地硬件上快速运行的双语模型。为此，我们开创性地以1:1英语-法语预训练数据比例、定制分词器和双语微调数据集训练了本质上的双语模型。我们公开发布训练数据集，其中包含法语部分——经人工精选的高质量多样化数据源。为评估非英语场景下的性能，我们构建了全新基准FrenchBench，该基准涵盖分类与生成任务，全面评估模型在法语中的各项性能。此外，基于透明性原则并促进大语言模型研究，我们开源了代码库、涵盖不同模型规模/训练数据分布/训练步骤的数十个检查点，以及微调后的对话模型和强翻译模型。我们通过FMTI框架评估模型，其透明度标准满足率达81%，远超多数开放项目。这项工作丰富了自然语言处理研究，突破了以往以英语为中心的研究范式，有助于加深对语言模型多语特性的理解。