master

ascend-robotfix dpo bug

7bb18c19创建于 2025年10月22日历史提交

文件	最后提交记录	最后更新时间
eplb_generate_map_ds.py	eplb 采集 Co-authored-by: yezhibei<yezhibei@huawei.com> # message auto-generated for no-merge-commit merge: merge master into master eplb 采集 Created-by: yezhibei Commit-by: yezhibei Merged-by: ascend-robot Description: eplb 采集 使用和验证说明wiki : EPLB 专家热度采集 https://wiki.huawei.com/wiki/WIKI202509268441609 See merge request: Ascend/MindSpeed-RL!641	11 个月前
preprocess_data.py	!546 修改路径校验 Merge pull request !546 from yzb/master	1 年前
train_dapo.py	update core0.12.1 Co-authored-by: daikang_123<daikang6@huawei.com> # message auto-generated for no-merge-commit merge: !671 merge master into master update core0.12.1 Created-by: daikang123 Commit-by: daikang123;daikang_123 Merged-by: ascend-robot Description: 长跑其他模型的验证结果：https://wiki.huawei.com/domains/6995/wiki/8/WIKI202510148565350 See merge request: Ascend/MindSpeed-RL!671	10 个月前
train_dpo.py	fix dpo bug Co-authored-by: daikang123<daikang6@huawei.com> # message auto-generated for no-merge-commit merge: !712 merge master into master fix dpo bug Created-by: daikang123 Commit-by: daikang123 Merged-by: ascend-robot Description: fix dpo bug See merge request: Ascend/MindSpeed-RL!712	10 个月前
train_grpo.py	update core0.12.1 Co-authored-by: daikang_123<daikang6@huawei.com> # message auto-generated for no-merge-commit merge: !671 merge master into master update core0.12.1 Created-by: daikang123 Commit-by: daikang123;daikang_123 Merged-by: ascend-robot Description: 长跑其他模型的验证结果：https://wiki.huawei.com/domains/6995/wiki/8/WIKI202510148565350 See merge request: Ascend/MindSpeed-RL!671	10 个月前
train_ppo.py	update core0.12.1 Co-authored-by: daikang_123<daikang6@huawei.com> # message auto-generated for no-merge-commit merge: !671 merge master into master update core0.12.1 Created-by: daikang123 Commit-by: daikang123;daikang_123 Merged-by: ascend-robot Description: 长跑其他模型的验证结果：https://wiki.huawei.com/domains/6995/wiki/8/WIKI202510148565350 See merge request: Ascend/MindSpeed-RL!671	10 个月前