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-hf] Fix exception in sentencepiece with added tokens #6320

Merged
merged 1 commit into from Mar 26, 2024
Merged

[convert-hf] Fix exception in sentencepiece with added tokens #6320

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.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
12 changes: 8 additions & 4 deletions convert-hf-to-gguf.py
View file
Open in desktop
Expand Up @@ -331,7 +331,7 @@ def _set_vocab_sentencepiece(self):
tokenizer = SentencePieceProcessor(str(tokenizer_path))
vocab_size = self.hparams.get('vocab_size', tokenizer.vocab_size())

for token_id in range(vocab_size):
for token_id in range(tokenizer.vocab_size()):
piece = tokenizer.id_to_piece(token_id)
text = piece.encode("utf-8")
score = tokenizer.get_score(token_id)
Expand All @@ -356,9 +356,13 @@ def _set_vocab_sentencepiece(self):
added_tokens_json = json.load(f)

for key in added_tokens_json:
tokens.append(key.encode("utf-8"))
scores.append(-1000.0)
toktypes.append(SentencePieceTokenTypes.USER_DEFINED)
key = key.encode("utf-8")
if key not in tokens:
tokens.append(key)
scores.append(-1000.0)
toktypes.append(SentencePieceTokenTypes.USER_DEFINED)

assert len(tokens) == vocab_size

self.gguf_writer.add_tokenizer_model("llama")
self.gguf_writer.add_token_list(tokens)
Expand Down