Update tokenization_chatglm.py
#72
by
JeremyHibiki
- opened
TensorType should come from transformers.utils instead of torch. Otherwise, the tokenizer can't be used alone in an environment without PyTorch installed, where we only need to count tokens.
tokenization_chatglm.py 有何用途,
ZHANGYUXUAN-zR
changed pull request status to
merged