Skip to content

Handle tokenizer configs without tokenizer_class #2278

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

Open
CodingFeng101 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Handle tokenizer configs without tokenizer_class #2278

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion litgpt/tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ def __init__(self, checkpoint_dir: Path | str) -> None:
self.apply_decoding_fix = None
if (config_path := checkpoint_dir / "tokenizer_config.json").is_file():
with open(config_path, encoding="utf-8") as fp:
self.apply_decoding_fix = "LlamaTokenizer" in json.load(fp)["tokenizer_class"]
self.apply_decoding_fix = "LlamaTokenizer" in (json.load(fp).get("tokenizer_class") or "")

@property
def vocab_size(self) -> int:
Expand Down
11 changes: 11 additions & 0 deletions tests/test_tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
# Copyright Lightning AI. Licensed under the Apache License 2.0, see LICENSE file.
import json
import os
import shutil
from pathlib import Path
Expand Down Expand Up @@ -112,6 +113,16 @@ def test_tokenizer_input_validation():
Tokenizer("cocofruit")


def test_tokenizer_config_without_tokenizer_class(tmp_path):
HFTokenizer(BPE()).save(str(tmp_path / "tokenizer.json"))
with open(tmp_path / "tokenizer_config.json", "w", encoding="utf-8") as fp:
json.dump({"add_bos_token": False}, fp)

tokenizer = Tokenizer(tmp_path)

assert tokenizer.apply_decoding_fix is False


@pytest.mark.parametrize("use_bos_by_default", (True, False))
@pytest.mark.parametrize("encode_use_bos", (None, True, False))
@pytest.mark.parametrize("encode_use_eos", (True, False))
Expand Down