We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
prefix
options
position
token_type
length
encoder
hidden_size
InputExample
InputFeatures
d_model
model_state
use_fast
fast_tokenizer
ERNIE
BERT
TinyBert
ERNIE-M
The text was updated successfully, but these errors were encountered:
我这边merge了一个关于text classification的PR, 可以加上 #3679
Sorry, something went wrong.
FrostML
wj-Mcat
w5688414
ZHUI
westfish
gongel
LiuChiachi
linjieccc
JunnYu
lugimzzz
No branches or pull requests
New Features
Prompt API
prefix
和options
,新增position
,token_type
,length
,encoder
,hidden_size
等7个属性 [prompt] update prompt api & add prefix template #3724InputExample
和InputFeatures
对输入数据关键字的限制问答
Trainer
FasterGeneration
d_model
4 倍的限制,新增导入model_state
方式加载模型 Lift restrictions to support more d_inner_hid #3592FastTokenizer
use_fast
参数,指定使用fast_tokenizer
完成高性能分词。目前ERNIE
,BERT
,TinyBert
以及ERNIE-M
可开启该选项。[FastTokenizer] Add clip fast tokenizer #3746基础底座
UIE
Neural Search
Text Classification
Bug Fix
PPDiffusers
Others
The text was updated successfully, but these errors were encountered: