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

convert : ignore tokens if their IDs are within [0, vocab_size) #3831

Merged
merged 1 commit into from
Oct 28, 2023
Merged

convert : ignore tokens if their IDs are within [0, vocab_size) #3831

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
21 changes: 12 additions & 9 deletions convert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -366,16 +366,19 @@ def __init__(self, fname_tokenizer: Path, fname_added_tokens: Path | None) -> No
added_tokens = {}

vocab_size: int = self.sentencepiece_tokenizer.vocab_size()
expected_ids = list(range(vocab_size, vocab_size + len(added_tokens)))
actual_ids = sorted(added_tokens.values())
if expected_ids != actual_ids:
raise Exception(f"Expected added token IDs to be sequential and start at {vocab_size}; got {actual_ids}")

items = sorted(added_tokens.items(), key=lambda text_idx: text_idx[1])
self.added_tokens_list = [text for (text, idx) in items]
self.vocab_size_base: int = vocab_size
self.vocab_size: int = self.vocab_size_base + len(self.added_tokens_list)
self.fname_tokenizer = fname_tokenizer
new_tokens = {id: piece for piece, id in added_tokens.items() if id >= vocab_size}
expected_new_ids = list(range(vocab_size, vocab_size + len(new_tokens)))
actual_new_ids = sorted(new_tokens.keys())

if expected_new_ids != actual_new_ids:
raise ValueError(f"Expected new token IDs {expected_new_ids} to be sequential; got {actual_new_ids}")

# Token pieces that were added to the base vocabulary.
self.added_tokens_list = [new_tokens[id] for id in actual_new_ids]
self.vocab_size_base = vocab_size
self.vocab_size = self.vocab_size_base + len(self.added_tokens_list)
self.fname_tokenizer = fname_tokenizer
self.fname_added_tokens = fname_added_tokens

def sentencepiece_tokens(self) -> Iterable[tuple[bytes, float, gguf.TokenType]]:
Expand Down