Tweak ESM tokenizer for Nucleotide Transformer #22770
Merged
Conversation
This file contains 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
amyeroberts
reviewed
Apr 14, 2023
| return cls + token_ids_0 | ||
| else: | ||
| return cls + token_ids_0 + sep | ||
| elif sep is None: |
There was a problem hiding this comment.
Should this be:
Suggested change
| elif sep is None: | |
| elif self.eos_token_id is None: |
as sep is always a list?
There was a problem hiding this comment.
I spotted that one just before you got here, and yes you're right!
|
The documentation is not available anymore as the PR was closed or merged. |
novice03
pushed a commit
to novice03/transformers
that referenced
this pull request
Jun 23, 2023
* If EOS is None, don't add it to sequences * If EOS is None, don't add it to sequences
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Outdated suggestions cannot be applied.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.
Nucleotide Transformer is a model that takes DNA inputs. It uses the same model architecture as the protein model ESM, but in addition to a different vocabulary it tokenizes inputs without a
<sep>or<eos>token at the end. This PR makes a small tweak to the tokenization code for ESM, so that it doesn't try to addself.eos_token_idto sequences when the tokenizer does not have aneos_tokenset. With this change, we can fully support Nucleotide Transformer as an ESM checkpoint.