Skip to content

revert masking vocab_size#4089

Merged
lvhan028 merged 4 commits intoInternLM:mainfrom
lvhan028:revert-mask-vocab-size
Oct 31, 2025
Merged

revert masking vocab_size#4089
lvhan028 merged 4 commits intoInternLM:mainfrom
lvhan028:revert-mask-vocab-size

Conversation

@lvhan028
Copy link
Copy Markdown
Collaborator

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Intern-S1 changed the tokenizer file. It return empty string when token_id is out of range [0, len(tokenizer)]
https://huggingface.co/internlm/Intern-S1-mini/discussions/6/files

Thus we can safely revert to the original version.

@lvhan028 lvhan028 requested a review from irexyc October 31, 2025 07:25
@lvhan028 lvhan028 merged commit 60aa80e into InternLM:main Oct 31, 2025
9 checks passed
Skyseaee pushed a commit to Skyseaee/lmdeploy that referenced this pull request Jan 4, 2026
* revert turbomind masking vocab size

* revert mask-vocab-size in pytorch engine

* fix typo

* update log
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants