[GH-ISSUE #42] Ablation studies for DeepSeekMoE #39

Open
opened 2026-10-26 21:01:58 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @JinjieNi on GitHub (Dec 13, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-MoE/issues/42

Hi Authors,

Thanks for presenting the great work of DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models.

Regarding the ablation study "Shared Expert Isolation." in section 4.4 and figure 3, may I check whether the models in Figure 3 are all trained from scratch or directly use the GShard results, especially the blue setting?

Thank you!

Originally created by @JinjieNi on GitHub (Dec 13, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-MoE/issues/42 Hi Authors, Thanks for presenting the great work of DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models. Regarding the ablation study "Shared Expert Isolation." in section 4.4 and figure 3, may I check whether the models in Figure 3 are all trained from scratch or directly use the GShard results, especially the blue setting? Thank you!
Sign in to join this conversation.
No labels
pull-request
WIP
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepSeek-MoE#39
No description provided.