docs: token_usage tokenizer zip bumped from deepseek-v3 to deepseek-v4 - #18
Open
github-actions[bot] wants to merge 1 commit into
Open
docs: token_usage tokenizer zip bumped from deepseek-v3 to deepseek-v4#18github-actions[bot] wants to merge 1 commit into
github-actions[bot] wants to merge 1 commit into
Conversation
DeepSeek swapped the offline tokenizer artifact referenced by the Token & Token Usage guide from `deepseek_v3_tokenizer.zip` to `deepseek_v4_tokenizer.zip`. This matters because that zip is what developers download to compute offline token counts for billing estimation — the v3 and v4 tokenizers use different tokenization methods, so anyone estimating tokens against the current v4 models with the old package would get incorrect counts. The change is an upstream signal that the v4 tokenizer is now the canonical reference, and it applies to both the English and Chinese mirror of the page. - Tokenizer artifact URL in `content/en/quick_start/token_usage.md` and `content/zh-cn/quick_start/token_usage.md` changed from `deepseek_v3_tokenizer.zip` to `deepseek_v4_tokenizer.zip` — developers caching or hotlinking the old zip should re-download, and offline token-count scripts should be re-validated against the v4 tokenizer. - `content/.metadata.json` now records that the `news250120` page (DeepSeek-R1 Release) served a fallback SPA shell instead of real content — that news page appears unfetchable in this snapshot, so any links into it may be stale; worth re-fetching/verifying separately. - `fetched:` date bumped to 2026-08-28 across the touched pages; `llms-full.txt` mirrors the tokenizer change.
github-actions
Bot
force-pushed
the
docs/sync
branch
from
August 28, 2026 22:26
f804802 to
19eff56
Compare
github-actions
Bot
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
DeepSeek swapped the offline tokenizer artifact referenced by the Token & Token Usage guide from
deepseek_v3_tokenizer.ziptodeepseek_v4_tokenizer.zip. This matters because that zip is what developers download to compute offline token counts for billing estimation — the v3 and v4 tokenizers use different tokenization methods, so anyone estimating tokens against the current v4 models with the old package would get incorrect counts. The change is an upstream signal that the v4 tokenizer is now the canonical reference, and it applies to both the English and Chinese mirror of the page.content/en/quick_start/token_usage.mdandcontent/zh-cn/quick_start/token_usage.mdchanged fromdeepseek_v3_tokenizer.ziptodeepseek_v4_tokenizer.zip— developers caching or hotlinking the old zip should re-download, and offline token-count scripts should be re-validated against the v4 tokenizer.content/.metadata.jsonnow records that thenews250120page (DeepSeek-R1 Release) served a fallback SPA shell instead of real content — that news page appears unfetchable in this snapshot, so any links into it may be stale; worth re-fetching/verifying separately.fetched:date bumped to 2026-08-28 across the touched pages;llms-full.txtmirrors the tokenizer change.