master

ascend-robot[pytorch][feature]Add RL algorithms (PPO, GRPO, DAPO)

ee9689e6创建于 2025年11月17日历史提交

文件	最后提交记录	最后更新时间
FSDP2	!3331 [pytorch][optimize]update recomputation configuration in FSDP2 Merge pull request !3331 from HanhuiChen/master	1 年前
checkpoint	[pytorch][feature]PLM-1.8B pretrain/sft Co-authored-by: EVA1<jingsiyu1@huawei.com> # message auto-generated for no-merge-commit merge: !3637 merge master into master [pytorch][feature]PLM-1.8B pretrain/sft Created-by: EVA1 Commit-by: EVA1 Merged-by: ascend-robot Description: 1.PLM-1.8B 模型支持：数据集格式转换、权重转换、微调、预训练； 2.精度已对齐，sft相对误差小于千分之一。 See merge request: Ascend/MindSpeed-LLM!3637	10 个月前
evaluate	!2183 新增cmmlu评估 Merge pull request !2183 from shenjiarun/master	1 年前
finetune	[pytorch][feature]PLM-1.8B pretrain/sft Co-authored-by: EVA1<jingsiyu1@huawei.com> # message auto-generated for no-merge-commit merge: !3637 merge master into master [pytorch][feature]PLM-1.8B pretrain/sft Created-by: EVA1 Commit-by: EVA1 Merged-by: ascend-robot Description: 1.PLM-1.8B 模型支持：数据集格式转换、权重转换、微调、预训练； 2.精度已对齐，sft相对误差小于千分之一。 See merge request: Ascend/MindSpeed-LLM!3637	10 个月前
rlhf	[pytorch][feature]Add RL algorithms (PPO, GRPO, DAPO) Co-authored-by: fh_188<fenghui32@huawei.com> # message auto-generated for no-merge-commit merge: !3613 merge fenzhi2 into master [pytorch][feature]Add RL algorithms (PPO, GRPO, DAPO) Created-by: weixin_44917616 Commit-by: fh_188 Merged-by: ascend-robot Description: Add RL algorithms (PPO, GRPO, DAPO) See merge request: Ascend/MindSpeed-LLM!3613	10 个月前