Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Check if the given token is a string #745

Merged
merged 3 commits into from
Mar 14, 2024
Merged

Check if the given token is a string #745

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
3fb5779
Check if the given token is a string
silverriver Mar 14, 2024
6a27887
Merge branch 'main' into patch-1
silverriver Mar 14, 2024
ce99fa4
Format code
silverriver Mar 14, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
8 changes: 6 additions & 2 deletions outlines/integrations/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,11 +52,15 @@ def adapt_tokenizer(tokenizer: PreTrainedTokenizerBase) -> PreTrainedTokenizerBa
tokenizer.vocabulary = tokenizer.get_vocab()
tokenizer.special_tokens = set(tokenizer.all_special_tokens)

def convert_token_to_string(token: str) -> str:
def convert_token_to_string(token: Union[str, bytes]) -> str:
string = tokenizer.convert_tokens_to_string([token])

# A hack to handle missing spaces to HF's Llama tokenizers
if token.startswith(SPIECE_UNDERLINE) or token == "<0x20>":
if (
type(token) is str
and token.startswith(SPIECE_UNDERLINE)
or token == "<0x20>"
):
return " " + string

return string
Expand Down