master

文件	最后提交记录	最后更新时间
base	[mindspeed-rl] 补充dapo和grpo规则奖励计算相关UT测试用例 Co-authored-by: McFlurry<zhangjianxiang3@huawei.com> # message auto-generated for no-merge-commit merge: !836 merge master into master [mindspeed-rl] 补充dapo和grpo规则奖励计算相关UT测试用例 Created-by: McFlurry100 Commit-by: McFlurry Merged-by: ascend-robot Description: 补充dapo和grpo规则奖励计算相关UT测试用例 See merge request: Ascend/MindSpeed-RL!836	7 个月前
loss	修改qwen25-32b的长序列精度问题、以及推20k随机步数oom Co-authored-by: d00613215<daikang6@huawei.com> # message auto-generated for no-merge-commit merge: !894 merge master into master 修改qwen25-32b的长序列精度问题、以及推20k随机步数oom Created-by: daikang123 Commit-by: d00613215 Merged-by: ascend-robot Description: 修改qwen25-32b推20k，随机步数后oom 修改qwen25-32b的长序列精度问题 See merge request: Ascend/MindSpeed-RL!894	6 个月前
__init__.py	!34 【修改说明】: 提交loss函数 Merge pull request !34 from Delphine/master	1 年前
test_actor.py	!470 reuse fp32 Merge pull request !470 from 戴康123/master	1 年前
test_actor_rollout_hybrid.py	!470 reuse fp32 Merge pull request !470 from 戴康123/master	1 年前
test_critic.py	!470 reuse fp32 Merge pull request !470 from 戴康123/master	1 年前
test_math_dapo.py	[mindspeed-rl] 补充dapo和grpo规则奖励计算相关UT测试用例 Co-authored-by: McFlurry<zhangjianxiang3@huawei.com> # message auto-generated for no-merge-commit merge: !836 merge master into master [mindspeed-rl] 补充dapo和grpo规则奖励计算相关UT测试用例 Created-by: McFlurry100 Commit-by: McFlurry Merged-by: ascend-robot Description: 补充dapo和grpo规则奖励计算相关UT测试用例 See merge request: Ascend/MindSpeed-RL!836	7 个月前
test_reference.py	!470 reuse fp32 Merge pull request !470 from 戴康123/master	1 年前
test_reward.py	!470 reuse fp32 Merge pull request !470 from 戴康123/master	1 年前
test_verifier.py	!470 reuse fp32 Merge pull request !470 from 戴康123/master	1 年前