We present Laguna M.1 and Laguna XS.2, two Mixture-of-Experts foundation models built for long-horizon, agentic coding: M.1 has $225.8$B total parameters ($23.4$B activated per token) and XS.2 has $33.4$B total ($3$B activated). Both models were trained from scratch end-to-end inside the same internal system that we refer to as our Model Factory: a tightly-integrated stack of versioned data, training, evaluation, and inference components that turn model development into an industrial process. We describe the principles and design choices of the Model Factory and also detail the end-to-end training process of our models, throughout pre-training data and architecture, post-training stages, evaluation, and quantization. On agentic software engineering and terminal benchmarks (SWE-bench Verified, SWE-bench Multilingual, SWE-Bench Pro, and Terminal-Bench 2.0) M.1 and XS.2 are competitive with state-of-the-art open models in their respective weight classes. Laguna XS.2 weights are released under Apache~2.0 at https://huggingface.co/collections/poolside/laguna-xs2.

翻译：我们介绍Laguna M.1和Laguna XS.2，两个基于混合专家架构的基座模型，专为长期、自主化的编码任务而设计：M.1总参数量为225.8B（每Token激活23.4B参数），XS.2总参数量为33.4B（每Token激活3B参数）。两个模型均在我们内部称为“模型工厂”的同一系统中从头开始端到端训练而成：该工厂是一个紧密集成的组件栈，涵盖版本化数据、训练、评估与推理，将模型开发转变为工业化流程。本文阐述了模型工厂的设计原则与决策，并详细介绍了我们模型从端到端训练的全过程，包括预训练数据与架构、后训练阶段、评估及量化。在自主化软件工程与终端基准测试（SWE-bench Verified、SWE-bench Multilingual、SWE-Bench Pro及Terminal-Bench 2.0）中，M.1和XS.2在各自权重等级内可与最先进的开源模型相匹敌。Laguna XS.2的权重已在Apache~2.0许可下发布于https://huggingface.co/collections/poolside/laguna-xs2。