| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
更新使用文档,修复在使用moe模型时忘加配置导致的推理乱码问题 2.3.0 Co-authored-by: Hcm03<chengminhua1@huawei.com> # message auto-generated for no-merge-commit merge: !824 merge 2.3.0 into 2.3.0 更新使用文档,修复在使用moe模型时忘加配置导致的推理乱码问题 2.3.0 Created-by: Hcm03 Commit-by: Hcm03 Merged-by: ascend-robot Description: update: 更新文件 dapo.md update: 更新文件 dpo.md update: 更新文件 grpo.md update: 更新文件 ppo.md See merge request: Ascend/MindSpeed-RL!824 | 8 个月前 | |
升级LLM分支到2.3.0 Co-authored-by: wangshuyang31<wangshuyang8@huawei.com> # message auto-generated for no-merge-commit merge: !850 merge 2.3.0 into 2.3.0 升级LLM分支到2.3.0 Created-by: wangshuyang31 Commit-by: wangshuyang31 Merged-by: ascend-robot Description: 升级LLM分支到2.3.0 并解决bug - DAPO qwen25-32b 长跑精度不上升的问题 同步MASTER分支中 https://gitcode.com/Ascend/MindSpeed-RL/pull/780 的修改。 验证结果: https://wiki.huawei.com/domains/64729/wiki/101438/WIKI202512179455316 https://wiki.huawei.com/domains/64729/wiki/101438/WIKI202512179454678 https://wiki.huawei.com/domains/64729/wiki/101438/WIKI202512179456584 See merge request: Ascend/MindSpeed-RL!850 | 8 个月前 | |
master readme文档修改 Co-authored-by: xiazhahe<nieshiyu1@huawei.com> # message auto-generated for no-merge-commit merge: !710 merge master into master master readme文档修改 Created-by: xiazhahe Commit-by: xiazhahe Merged-by: ascend-robot Description: master readme文档修改 See merge request: Ascend/MindSpeed-RL!710 | 9 个月前 | |
更新资料 - install guild with new cann Co-authored-by: wangshuyang31<wangshuyang8@huawei.com> # message auto-generated for no-merge-commit merge: !878 merge 2.3.0-1230 into 2.3.0 更新资料 - install guild with new cann Created-by: wangshuyang31 Commit-by: wangshuyang31 Merged-by: ascend-robot Description: update install guild with new cann and 2.3.0 intro See merge request: Ascend/MindSpeed-RL!878 | 7 个月前 |
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
| 8 个月前 | ||
| 8 个月前 | ||
| 9 个月前 | ||
| 7 个月前 |