Added hybrid quantization for seq2seq models #427
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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. |
AlexKoff88
changed the title
echarlaix
reviewed
Dec 15, 2023
Comment on lines
+288
to
+291
| # Compress weights of decoders for safity | ||
| self.model.decoder_model = nncf.compress_weights(self.model.decoder_model) | ||
| if self.model.use_cache: | ||
| self.model.decoder_with_past_model = nncf.compress_weights(self.model.decoder_with_past_model) |
There was a problem hiding this comment.
Would there be a possibility to also quantize the activations for the decoder components?
There was a problem hiding this comment.
It is possible but it may hurt accuracy.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This is a draft of the PR that should be merged after OpenVINO 2023.1 release