refactor: 从data 模块分离tokenizer

This commit is contained in:
2026-04-04 16:12:58 +08:00
parent b531232a9b
commit bd9741dc5f
16 changed files with 108 additions and 92 deletions
+1 -1
View File
@@ -11,7 +11,7 @@ from tokenizers import pre_tokenizers
from torch.utils.data import Dataset
from astrai.config.model_config import ModelConfig
from astrai.data.tokenizer import BpeTokenizer, BpeTrainer
from astrai.tokenizer import BpeTokenizer, BpeTrainer
from astrai.model.transformer import Transformer