add Multilingual E5 models #2
Open
Conversation
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
Author
|
This is a benchmark review for experiment This pull request was cloned from |
brendanator
commented
Apr 9, 2024
Author
brendanator
left a comment
brendanator
left a comment
There was a problem hiding this comment.
Hey @brendanator - I've reviewed your changes and they look great!
Here's what I looked at during the review
- 🟢 General issues: all looks good
- 🟢 Security: all looks good
- 🟢 Testing: all looks good
- 🟢 Complexity: all looks good
- 🟡 Docstrings: 1 issue found
Help me be more useful! Please click 👍 or 👎 on each comment to tell me if it was helpful.
| } | ||
|
|
||
| /// Private method to return an instance | ||
| fn new(tokenizer: Tokenizer, session: Session) -> Self { |
Author
There was a problem hiding this comment.
TextEmbedding::new
Reason for update: The function signature and internal logic have changed to include a new field need_token_type_ids.
Suggested new docstring:
/// Private method to return an instance, determining if `token_type_ids` are needed based on the session inputs.
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Outdated suggestions cannot be applied.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.
This PR adds intfloat/multilingual-e5-base, -small models.
these models have no "token_type_ids" inputs, so I introduce check logic.
curiously, intfloat/multilingual-e5-large onnx model is only 546kB(small is 470MB, base is 1.11GB). and it can't run inference. so, I commented out for large model definition.