Improve: Make it possible to convert BERT language models to FP16

This commit is contained in:
tsukumi
2024-12-19 07:16:59 +09:00
parent e642a4cb69
commit c1fce3fec7
4 changed files with 259 additions and 11 deletions

View File

@@ -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'