fix bos token missing #346
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
guipenedo
reviewed
Apr 29, 2025
| local_working_dir: DataFolderLike | None = None, | ||
| save_filename: str = None, # if defined, the final output filename will be this | ||
| tokenizer_name_or_path: str = "gpt2", # tokenizer to use, from HF or a local | ||
| bos_token: str = "<|startoftext|>", # whether to add the BOS token nefore each document |
Collaborator
There was a problem hiding this comment.
Suggested change
| bos_token: str = "<|startoftext|>", # whether to add the BOS token nefore each document | |
| bos_token: str | None = None, # whether to add the BOS token nefore each document |
should disable it by default
Comment on lines
+54
to
+65
| elif self.bos_token is not None or self.eos_token is not None: | ||
| special_tokens = [] | ||
| if self.bos_token: | ||
| special_tokens.append(("<BOS>", self.tokenizer.token_to_id(self.bos_token))) | ||
| if self.eos_token: | ||
| special_tokens.append(("<EOS>", self.tokenizer.token_to_id(self.eos_token))) | ||
| if self.bos_token and not self.eos_token: | ||
| single = "<BOS> $A" | ||
| elif self.eos_token and not self.bos_token: | ||
| single = "$A <EOS>" | ||
| else: | ||
| single = "<BOS> $A <EOS>" |
Collaborator
There was a problem hiding this comment.
Suggested change
| elif self.bos_token is not None or self.eos_token is not None: | |
| special_tokens = [] | |
| if self.bos_token: | |
| special_tokens.append(("<BOS>", self.tokenizer.token_to_id(self.bos_token))) | |
| if self.eos_token: | |
| special_tokens.append(("<EOS>", self.tokenizer.token_to_id(self.eos_token))) | |
| if self.bos_token and not self.eos_token: | |
| single = "<BOS> $A" | |
| elif self.eos_token and not self.bos_token: | |
| single = "$A <EOS>" | |
| else: | |
| single = "<BOS> $A <EOS>" | |
| elif self.bos_token is not None or self.eos_token is not None: | |
| special_tokens = [] | |
| single_elems = [] | |
| if self.bos_token: | |
| special_tokens.append(("<BOS>", self.tokenizer.token_to_id(self.bos_token))) | |
| single_elems.append("<BOS>") | |
| single_elems.append("$A") | |
| if self.eos_token: | |
| special_tokens.append(("<EOS>", self.tokenizer.token_to_id(self.eos_token))) | |
| single_elems.append("<EOS>") |
| self._tokenizer.post_processor = TemplateProcessing( | ||
| single="$A <EOS>", | ||
| special_tokens=[("<EOS>", self.tokenizer.token_to_id(self.eos_token))], | ||
| single=single, |
Collaborator
There was a problem hiding this comment.
Suggested change
| single=single, | |
| single=" ".join(single_elems), |
Collaborator
|
hi, can you please make this pr editable by maintainers? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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 fixes #345 by checking for all three combinations of bos/eos existence and using an appropriate template for each case