This repository has been archived by the owner on Jan 15, 2024. It is now read-only.
Quantize QuestionAnswering models #1581
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 2 commits
October 6, 2021 11:18
|
The documentation website for preview: http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR1581/bc9ce0f899079a3cf1a8d80bbb1fb746dd3c69b5/index.html |
anko-intel
approved these changes
Oct 6, 2021
scripts/question_answering/models.py
Outdated
| @@ -287,10 +289,14 @@ def forward(self, tokens, token_types, valid_length, p_mask, start_position): | |||
| Shape (batch_size, sequence_length) | |||
| answerable_logits | |||
| """ | |||
| backbone_net = self.backbone | |||
| if self.quantized: | |||
There was a problem hiding this comment.
Suggested change
| if self.quantized: | |
| if self.quantized_bacbone is not None: |
end remove quantized ?
There was a problem hiding this comment.
I thought about it, but I remained this quantized flag as switch on/off of quantized model - not sure if it is really usable. What do you think?
|
The documentation website for preview: http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR1581/bba1525cc4ac848aca3ed452dbc15f43d8e53afb/index.html |
|
The documentation website for preview: http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR1581/f2b5043608cbc68c0b67fbdcf2a3a3ef85363921/index.html |
This was referenced Dec 2, 2021
added 2 commits
March 8, 2022 16:53
bartekkuncer
approved these changes
Apr 8, 2022
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR enables quantization on question answering scripts.
Added custom calibration collector to avoid significant accuracy drop