mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-11 13:30:35 +00:00
convert-hf : change assert to exception (#8015)
This commit is contained in:
parent
5b48cd53a8
commit
3aa184a8c7
@ -967,7 +967,13 @@ class XverseModel(Model):
|
||||
from transformers import AutoTokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained(dir_model)
|
||||
vocab_size = hparams.get("vocab_size", len(tokenizer.vocab))
|
||||
assert max(tokenizer.vocab.values()) < vocab_size
|
||||
# Since we are checking the maximum index, we need to ensure it's strictly less than vocab_size,
|
||||
# because vocab_size is the count of items, and indexes start at 0.
|
||||
max_vocab_index = max(tokenizer.get_vocab().values())
|
||||
if max_vocab_index >= vocab_size:
|
||||
raise ValueError("Vocabulary size exceeds expected maximum size.")
|
||||
|
||||
|
||||
|
||||
reverse_vocab: dict[int, str] = {id_: encoded_tok for encoded_tok, id_ in tokenizer.vocab.items()}
|
||||
added_vocab = tokenizer.get_added_vocab()
|
||||
|
Loading…
Reference in New Issue
Block a user