GPT2Config
This commit is contained in:
parent
c13bfa037a
commit
240e9c4535
@ -66,6 +66,7 @@ def encode(filepath: str, blocksize: int, vocabsize: int, ouputdir: Path, verbos
|
||||
|
||||
from aitextgen.TokenDataset import TokenDataset
|
||||
from aitextgen.tokenizers import train_tokenizer
|
||||
from transformers import GPT2Config
|
||||
|
||||
#NOTE: vocab_size is fixed since this is not yet in train_tokenizer
|
||||
#see https://github.com/minimaxir/aitextgen/blob/master/aitextgen/tokenizers.py
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user