Improve: Make it possible to convert BERT language models to FP16
This commit is contained in:
@@ -12,6 +12,7 @@ nltk<=3.8.1
|
||||
num2words
|
||||
numpy<2
|
||||
onnx
|
||||
onnxconverter-common
|
||||
onnxruntime
|
||||
onnxruntime-directml; sys_platform == 'win32'
|
||||
onnxruntime-gpu; sys_platform != 'darwin'
|
||||
|
||||
Reference in New Issue
Block a user