| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
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 | |
| 1 年前 | ||
| 1 年前 | ||
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 | |
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 | |
| 1 年前 | ||
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 | |
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 | |
| 1 年前 | ||
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 | |
fix deepseekr1 train_step and kl_coef Co-authored-by: wucong25<wucong25@huawei.com> # message auto-generated for no-merge-commit merge: !681 merge wucong/fix_deepseek_step into master fix deepseekr1 train_step and kl_coef Created-by: wucong25 Commit-by: wucong25 Merged-by: ascend-robot Description: fix deepseekr1 train_step and kl_coef See merge request: Ascend/MindSpeed-RL!681 | 11 个月前 | |
fix deepseekr1 train_step and kl_coef Co-authored-by: wucong25<wucong25@huawei.com> # message auto-generated for no-merge-commit merge: !681 merge wucong/fix_deepseek_step into master fix deepseekr1 train_step and kl_coef Created-by: wucong25 Commit-by: wucong25 Merged-by: ascend-robot Description: fix deepseekr1 train_step and kl_coef See merge request: Ascend/MindSpeed-RL!681 | 11 个月前 | |
fix dynamic_batch_size and eplb for ds671B Co-authored-by: McFlurry<zhangjianxiang3@huawei.com> # message auto-generated for no-merge-commit merge: merge master into master fix dynamic_batch_size and eplb for ds671B Created-by: McFlurry100 Commit-by: McFlurry Merged-by: ascend-robot Description: fix dynamic_batch_size and eplb for ds671B See merge request: Ascend/MindSpeed-RL!611 | 11 个月前 | |
fix grpo loss&reward Co-authored-by: may_feimei<meifei5@huawei.com> # message auto-generated for no-merge-commit merge: merge master into master fix grpo loss&reward Created-by: may_feimei Commit-by: may_feimei Merged-by: ascend-robot Description: 修复训崩 See merge request: Ascend/MindSpeed-RL!669 | 11 个月前 | |
fix grpo qwen25 32b A3 reward Co-authored-by: wucong25<wucong25@huawei.com> # message auto-generated for no-merge-commit merge: merge wucong/fix_reward into master fix grpo qwen25 32b A3 reward Created-by: wucong25 Commit-by: wucong25 Merged-by: ascend-robot Description: fix grpo qwen25 32b A3 reward See merge request: Ascend/MindSpeed-RL!665 | 11 个月前 | |
| 1 年前 | ||
| 1 年前 | ||
| 1 年前 | ||
| 1 年前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 10 个月前 | ||
| 1 年前 | ||
| 1 年前 | ||
| 10 个月前 | ||
| 10 个月前 | ||
| 1 年前 | ||
| 10 个月前 | ||
| 10 个月前 | ||
| 1 年前 | ||
| 10 个月前 | ||
| 11 个月前 | ||
| 11 个月前 | ||
| 11 个月前 | ||
| 11 个月前 | ||
| 11 个月前 | ||
| 1 年前 | ||
| 1 年前 | ||
| 1 年前 | ||
| 1 年前 |