Post-training alignment is central to deploying large language models (LLMs), yet practical workflows remain split across backend-specific tools and ad-hoc glue code, making experiments hard to reproduce. We identify backend interference, reward fragmentation, and irreproducible pipelines as key obstacles in alignment research. We introduce AlignTune, a modular toolkit exposing a unified interface for supervised fine-tuning (SFT) and RLHF-style optimization with interchangeable TRL and Unsloth backends. AlignTune standardizes configuration, provides an extensible reward layer (rule-based and learned), and integrates evaluation over standard benchmarks and custom tasks. By isolating backend-specific logic behind a single factory boundary, AlignTune enables controlled comparisons and reproducible alignment experiments.

翻译：训练后对齐是部署大型语言模型（LLM）的核心环节，然而实际工作流程仍分散在特定后端工具和临时粘合代码中，导致实验难以复现。我们识别出后端干扰、奖励分散以及不可复现的流程是对齐研究的主要障碍。本文介绍AlignTune——一个模块化工具包，它通过可互换的TRL与Unsloth后端，为监督微调（SFT）和RLHF式优化提供了统一接口。AlignTune标准化了配置流程，提供了可扩展的奖励层（包括基于规则和学习的奖励），并集成了对标准基准测试与定制任务的评估功能。通过将后端特定逻辑隔离在统一的工厂接口之后，AlignTune实现了可控的对比研究与可复现的对齐实验。