LowinLi / transformers-stream-generator

This is a text generation method which returns a generator, streaming out each token in real-time during inference, based on Huggingface/Transformers.
MIT License
96 stars 14 forks source link

do_sample=False #1

Open vicwer opened 1 year ago

vicwer commented 1 year ago

do_sample=True时可以流式输出,设置为False时就一次输出了。

LowinLi commented 1 year ago

do_sample=True时可以流式输出,设置为False时就一次输出了。

Hi,Readme我有提到,只支持了do_sample=True readme

arashStone commented 1 year ago

这个仓库很棒,帮大忙了,同时请问后续有计划支持do_sample=False时的流式输出吗?