deepseek-ai/DeepSeek-MoE
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-MoE.git synced 2026-11-05 00:57:43 +00:00
Code Issues 24 Projects Packages Wiki Activity

[GH-ISSUE #14] The released DeepSeekMoE 16B Base has 3 different vocab size #12

New issue
Closed
opened 2026-10-26 21:01:37 +00:00 by bsakaguchi · 2 comments
bsakaguchi commented 2026-10-26 21:01:37 +00:00
Owner
Copy link

Originally created by @drxmy on GitHub (Jan 19, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-MoE/issues/14

In config.json, vocab size says 102400 which is the same as the shape of "model.embed_tokens.weight".
But tokenizer.vocab_size says 100000 and len(tokenizer) gives 100015. I have not dig deeper into the code. Is this intended or some bug?

Thank you!

Originally created by @drxmy on GitHub (Jan 19, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-MoE/issues/14 In config.json, vocab size says 102400 which is the same as the shape of "model.embed_tokens.weight". But tokenizer.vocab_size says 100000 and len(tokenizer) gives 100015. I have not dig deeper into the code. Is this intended or some bug? Thank you!
bsakaguchi commented 2026-10-26 21:01:38 +00:00
Author
Owner
Copy link

@DeepSeekPH commented on GitHub (Jan 22, 2024):

Hi, you can find the answer on Page-5 of our LLM technique report https://arxiv.org/pdf/2401.02954.pdf .
image

<!-- gh-comment-id:1903048444 --> @DeepSeekPH commented on GitHub (Jan 22, 2024): Hi, you can find the answer on Page-5 of our LLM technique report https://arxiv.org/pdf/2401.02954.pdf . <img width="732" alt="image" src="https://github.com/deepseek-ai/DeepSeek-MoE/assets/152240452/edbd28e3-3f7e-4613-bcf8-d74652089245">
bsakaguchi commented 2026-10-26 21:01:38 +00:00
Author
Owner
Copy link

@drxmy commented on GitHub (Jan 22, 2024):

Hi, you can find the answer on Page-5 of our LLM technique report https://arxiv.org/pdf/2401.02954.pdf . image

Thank you，I only read the moe paper

<!-- gh-comment-id:1903433456 --> @drxmy commented on GitHub (Jan 22, 2024): > Hi, you can find the answer on Page-5 of our LLM technique report https://arxiv.org/pdf/2401.02954.pdf . <img alt="image" width="732" src="https://private-user-images.githubusercontent.com/152240452/298443312-edbd28e3-3f7e-4613-bcf8-d74652089245.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MDU5MTAxMzAsIm5iZiI6MTcwNTkwOTgzMCwicGF0aCI6Ii8xNTIyNDA0NTIvMjk4NDQzMzEyLWVkYmQyOGUzLTNmN2UtNDYxMy1iY2Y4LWQ3NDY1MjA4OTI0NS5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwMTIyJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDEyMlQwNzUwMzBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1jN2Q3MjM0NjRjZWRiNGRjYzVhZmZhMjVlMjJjMDJmYTcwMTNmNTFiZDRhZmJjZDEyMjA0MDk5NDk4NDAwYzE4JlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.x78Xd5PGYrRL9PBivwdNf-f_XmHlTHZsopPllz3BQOU"> Thank you，I only read the moe paper
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

  
WIP
No labels
pull-request
WIP
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
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#12
No description provided.