mst272

LLM-Dojo. 轻量级 LLM Post-training 框架，支持 SFT、RLVR、On-Policy KD、Guide KD 及混合训练；实现单轮/多轮 Guide 蒸馏、多教师蒸馏、Reward 混合训练与自动化数据分流👩‍🎓👨‍🎓

transformer-pytorch. A pytorch Implementation of the Transformer: Attention Is All You Need

simple-lora-plus. A simple implementation of LoRA+: Efficient Low Rank Adaptation of Large Models