[GH-ISSUE #348] DeepSeek-R1 Models 's Activated Params #268

New issue

Closed

opened 2026-10-26 21:18:20 +00:00 by bsakaguchi · 1 comment

bsakaguchi commented

2026-10-26 21:18:20 +00:00

Owner

Originally created by @RyanOvO on GitHub (Feb 10, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/348

If I were to deploy based on DeepSeek R1, would the model parameters (i.e. the number of parameters used) for each activation look like this?

Will R1 exceed the call of the 37B parameter during training(fine-tune) ?
Will the activation parameter of 37B be exceeded during inference?

Originally created by @RyanOvO on GitHub (Feb 10, 2025). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/348 If I were to deploy based on DeepSeek R1, would the model parameters (i.e. the number of parameters used) for each activation look like this? ![Image](https://github.com/user-attachments/assets/cd391560-c650-4988-8fb3-c387d2c7c209) Will R1 exceed the call of the 37B parameter during training(fine-tune) ? Will the activation parameter of 37B be exceeded during inference?

bsakaguchi

2026-10-26 21:18:20 +00:00

closed this issue
added the
stale
label

bsakaguchi commented

2026-10-26 21:18:22 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (Mar 25, 2025):

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!

@github-actions[bot] commented on GitHub (Mar 25, 2025): This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you believe this issue is still relevant, please leave a comment to keep it open. Thank you for your contributions!