Skip to content

Fix vocabulary merge count accumulation #40

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
SYSTEMS-OPERATOR merged 1 commit into from
Jun 27, 2025
+11 −1
Merged

Fix vocabulary merge count accumulation #40

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: 5 additions & 1 deletion model/tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -355,7 +355,11 @@ def merge_vocab(pair: Tuple[str, str], v_in: Dict[str, int]) -> Dict[str, int]:
p = re.compile(r'(?<!\S)' + bigram + r'(?!\S)')
for word in v_in:
w_out = p.sub(''.join(pair), word)
v_out[w_out] = v_in[word]
# Combine counts if multiple words collapse into the same token
if w_out in v_out:
v_out[w_out] += v_in[word]
else:
v_out[w_out] = v_in[word]

return v_out

Expand Down
6 changes: 6 additions & 0 deletions tests/test_tokenizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,12 @@ def test_merge_vocab():
assert 'a b' not in merged


def test_merge_vocab_accumulates_counts():
vocab = {'a b c': 2, 'ab c': 1}
merged = merge_vocab(('a', 'b'), vocab)
assert merged['ab c'] == 3


def test_save_load_roundtrip(tmp_path):
freqs = {
'a': 1,
Expand Down