Update ibert.rst (#10445)
This commit is contained in:
committed by
GitHub
parent
aeba4f95bb
commit
3c733f3208
@@ -16,7 +16,7 @@ I-BERT
|
|||||||
Overview
|
Overview
|
||||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||||
|
|
||||||
The I-BERT model was proposed in `I-BERT: Integer-only BERT Quantization <https://arxiv.org/abs/2006.10220>`__ by
|
The I-BERT model was proposed in `I-BERT: Integer-only BERT Quantization <https://arxiv.org/abs/2101.01321>`__ by
|
||||||
Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney and Kurt Keutzer. It's a quantized version of RoBERTa running
|
Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney and Kurt Keutzer. It's a quantized version of RoBERTa running
|
||||||
inference up to four times faster.
|
inference up to four times faster.
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user