Guard embedder inputs against maxPositionEmbeddings#163
Open
alankessler wants to merge 1 commit intoml-explore:mainfrom
Open
Guard embedder inputs against maxPositionEmbeddings#163alankessler wants to merge 1 commit intoml-explore:mainfrom
alankessler wants to merge 1 commit intoml-explore:mainfrom
Conversation
BERT models crash when input exceeds maxPositionEmbeddings because the position embedding table is fixed-size. Truncate with a warning rather than crashing. Expose maxPositionEmbeddings on the EmbeddingModel protocol (default nil, non-breaking) so callers can check the limit and pre-truncate or chunk as needed. Fixes ml-explore#62.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #62.
BERT models crash when input exceeds
maxPositionEmbeddingsbecause the position embedding table is fixed-size. Per the discussion between @davidkoski and @anishbasu, this truncates with a warning rather than crashing.Also exposes
maxPositionEmbeddingson theEmbeddingModelprotocol (defaultnil, non-breaking) so callers who want to chunk or split long inputs can check the limit themselves.Qwen3 and Gemma3 use RoPE — no change needed.