questions regarding dimensions oftokens

[WeiLi9811]

Hi， Jihye！
Thanks so much for opening your code!
But I kept facing such error after running the first 2 modules, here's my problem:
after running :
import torch
from torchtext.legacy import data

TEXT = data.Field(tokenize = 'spacy',
tokenizer_language = 'en_core_web_sm')

LABEL = data.LabelField()

TEXT.build_vocab(train_data,
vectors = "glove.6B.100d",
unk_init = torch.Tensor.normal_)

LABEL.build_vocab(train_data)

i got the errors as below:
RuntimeError: Vector for token b'u-21s' has 96 dimensions, but previously read vectors have 100 dimensions. All vectors must have the same number of dimensions.

Is there any possible solution for this problem?