Spaces:
Running
Running
File size: 324 Bytes
751936e 9495a4f 751936e 428b731 9495a4f |
1 2 3 4 5 6 7 8 9 10 11 |
from transformers import AutoTokenizer
from vocab import TokenizerType
tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan2-7B-Chat", trust_remote_code=True)
# byte-bpe sentencepiece
tokenizer.type = TokenizerType.ByteBPE
tokenizer.comments = "expand the vocqbulary size from 64000 in Baichuan1 to 125696"
|