Skip to content

chore: fix formatting #2

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

Merged
pbillaut merged 1 commit into from
May 24, 2025
Merged

chore: fix formatting #2

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
6 changes: 3 additions & 3 deletions llm/tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@

Vocab: TypeAlias = dict[str, int]

NAIVE_TOKENS = re.compile(r'''([_,.;:?!"'()]|--|\s)''')
NAIVE_TOKENS = re.compile(r"""([_,.;:?!"'()]|--|\s)""")


def generate_vocab(tokens: list[str]) -> Vocab:
Expand All @@ -16,7 +16,7 @@ def naive_tokenization(text: str) -> list[str]:
return [text.strip() for text in tokens if text.strip()]


DECODE_PATTERN = re.compile(r'''\s+([,.?!"'()])''')
DECODE_PATTERN = re.compile(r"""\s+([,.?!"'()])""")


class SimpleTokenizerV1:
Expand All @@ -34,5 +34,5 @@ def encode(self, text: str) -> list[int]:

def decode(self, token_ids: list[int]) -> str:
text = " ".join([self.int_to_str[i] for i in token_ids])
text = DECODE_PATTERN.sub(r'\1', text)
text = DECODE_PATTERN.sub(r"\1", text)
return text
4 changes: 2 additions & 2 deletions tests/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,6 @@
import pytest


@pytest.fixture(scope='session')
@pytest.fixture(scope="session")
def resource() -> Path:
return Path(__file__).parent / 'resources'
return Path(__file__).parent / "resources"
16 changes: 13 additions & 3 deletions tests/test_tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@


def test_naive_tokenizer_the_verdict(resource: Path):
path = resource / 'the-verdict.txt'
path = resource / "the-verdict.txt"
raw_text = path.read_text()
tokens = naive_tokenization(raw_text)
assert len(tokens) == 4690
Expand All @@ -17,7 +17,17 @@ def test_generate_vocabulary():
vocab_tokens = naive_tokenization(text)
vocab = generate_vocab(vocab_tokens)

assert vocab == {'The': 0, 'brown': 1, 'dog': 2, 'fox': 3, 'jumps': 4, 'lazy': 5, 'over': 6, 'quick': 7, 'the': 8}
assert vocab == {
"The": 0,
"brown": 1,
"dog": 2,
"fox": 3,
"jumps": 4,
"lazy": 5,
"over": 6,
"quick": 7,
"the": 8,
}


class TestSimpleTokenizerV1:
Expand All @@ -36,7 +46,7 @@ def test_encode(self, vocab: Vocab):

def test_encode_fails_for_token_not_in_vocab(self, vocab: Vocab):
tokenizer = SimpleTokenizerV1(vocab)
unknown_token = 'elephant'
unknown_token = "elephant"
with pytest.raises(KeyError, match=unknown_token):
tokenizer.encode(f"The quick brown {unknown_token} jumps over the lazy dog")

Expand Down