Instella：性能卓越的完全开放语言模型

摘要

尽管大型语言模型（LLMs）在广泛任务中展现出卓越性能，但多数高性能模型仍保持闭源或部分开放，限制了研究的透明度与可复现性。本研究推出Instella系列——完全基于开放数据和代码库训练、参数量达三十亿的全开源语言模型家族。依托AMD Instinct MI300X GPU的算力支持，Instella通过大规模预训练、通用指令微调以及与人类偏好的对齐训练完成开发。尽管预训练词元数量显著少于同期多数模型，Instella在完全开源模型中实现了最先进的性能，并与同规模领先的开放权重模型相媲美。我们进一步发布两个专项优化版本：支持128K词元上下文长度的Instella-Long，以及通过数学任务监督微调与强化学习增强的推理专用模型Instella-Math。这些成果共同确立了Instella作为透明、高效、多功能的开源替代方案，推动语言建模研究向开放可复现的目标迈进。

English

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks, yet the majority of high-performing models remain closed-source or partially open, limiting transparency and reproducibility. In this work, we introduce Instella, a family of fully open three billion parameter language models trained entirely on openly available data and codebase. Powered by AMD Instinct MI300X GPUs, Instella is developed through large-scale pre-training, general-purpose instruction tuning, and alignment with human preferences. Despite using substantially fewer pre-training tokens than many contemporaries, Instella achieves state-of-the-art results among fully open models and is competitive with leading open-weight models of comparable size. We further release two specialized variants: Instella-Long, capable of handling context lengths up to 128K tokens, and Instella-Math, a reasoning-focused model enhanced through supervised fine-tuning and reinforcement learning on mathematical tasks. Together, these contributions establish Instella as a transparent, performant, and versatile alternative for the community, advancing the goal of open and reproducible language modeling research.

Instella：性能卓越的完全开放语言模型

Instella: Fully Open Language Models with Stellar Performance

摘要

Support