美團 LongCat 釋出 LongCat-Image-Dev 開發版
meituan-longcat/LongCat-Image-Dev
美團 LongCat 釋出 LongCat-Image-Dev,作為 LongCat-Image 的開發版本及中期訓練檢查點,供社羣進行下游開發。項目亦附有 SFT、LoRA 微調、DPO/GRPO/MPO 對齊及專項 Edit 訓練程式碼,並提供由預訓練資料整理至獎勵模型整合的可重現流程。
Introduction
LongCat-Image-Dev is a development variant of LongCat-Image, representing a mid-training checkpoint that is released to facilitate downstream development by the community, such as secondary fine-tuning via SFT, LoRA, and other customization methods.
Key Features
🔧 True Developer-Ready Foundation: Unlike typical release-the-final-model-only approaches, we provide the Dev—a high-plasticity, unconstrained state that avoids RL-induced rigidity. This enables seamless fine-tuning without fighting against over-aligned parameter spaces.
🛠️ Full-Stack Training Framework: We ship production-ready code for SFT, LoRA fine-tuning, DPO/GRPO/MPO alignment, and specialized Edit training. Every stage from pre-training data curation to reward model integration is reproducible, empowering researchers to build on our exact pipeline rather than reverse-engineering it.
來源:美團 LongCat:HuggingFace 新模型 · huggingface.co