CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Georgi Gerganov
2023-10-28 15:25:15 +03:00
committed by GitHub
parent bd6d9e2059
commit 8a2f2fea29
1 changed files with 12 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
convert.py
View File

@@ -366,16 +366,19 @@ class SentencePieceVocab:
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]]: