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

[Experimental] Add GPTNeoXTokenizer support to HFTokenizerConverter #678

Draft
wants to merge 3 commits into
base: main
Choose a base branch
from
Draft

[Experimental] Add GPTNeoXTokenizer support to HFTokenizerConverter #678

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
087aa1e
Improve handling of missing `vocab_file` attribute in HFTokenizerConv…
kazssym Mar 24, 2024
6f51aa2
Merge branch 'main' into bugfix/hf-missing-vocab_file
kazssym Mar 24, 2024
6f5311c
[Experimental] Add GPTNeoXTokenizer support to HFTokenizerConverter
kazssym Mar 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions onnxruntime_extensions/_hf_cvt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,10 +43,11 @@ def convert_json_vocab(hf_tokenizer):
f"{hf_tokenizer.__name__}: vocab_files_names is not found")

tokenizer_file = filenames["tokenizer_file"]
if (hf_tokenizer.vocab_file is None) or (not os.path.exists(hf_tokenizer.vocab_file)):
vocab_file = getattr(hf_tokenizer, "vocab_file", None)
if (vocab_file is None) or (not os.path.exists(vocab_file)):
model_dir = hf_tokenizer.name_or_path
else:
model_dir = os.path.dirname(hf_tokenizer.vocab_file)
model_dir = os.path.dirname(vocab_file)
tokenizer_json = json.load(
open(os.path.join(model_dir, tokenizer_file), "r", encoding="utf-8"))
# get vocab object from json file
Expand Down Expand Up @@ -181,6 +182,8 @@ def spm_decoder(self, **kwargs):
'BpeDecoder', HFTokenizerConverter.bpe_decoder, None),
"CodeGenTokenizer": TokenOpParam('GPT2Tokenizer', HFTokenizerConverter.bpe_tokenizer,
'BpeDecoder', HFTokenizerConverter.bpe_decoder, None),
"GPTNeoXTokenizer": TokenOpParam('GPT2Tokenizer', HFTokenizerConverter.bpe_tokenizer,
'BpeDecoder', HFTokenizerConverter.bpe_decoder, None),
"CLIPTokenizer": TokenOpParam('CLIPTokenizer', HFTokenizerConverter.clip_tokenizer,
'BpeDecoder', HFTokenizerConverter.bpe_decoder, None),
"RobertaTokenizer": TokenOpParam('RobertaTokenizer', HFTokenizerConverter.roberta_tokenizer,
Expand Down
Loading