Add Embedding quantization #4159
Merged
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
|
Thanks for your contribution! |
Codecov Report
@@ Coverage Diff @@
## develop #4159 +/- ##
===========================================
- Coverage 36.39% 36.38% -0.02%
===========================================
Files 419 419
Lines 59059 59089 +30
===========================================
+ Hits 21496 21499 +3
- Misses 37563 37590 +27
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
wawltor
reviewed
Dec 21, 2022
| self.quant(input_dir, args.strategy) | ||
| elif args.strategy == "qat": | ||
| output_dir_list = self.quant(input_dir, "ptq") | ||
| print(output_dir_list) |
| @@ -138,7 +153,7 @@ def _dynabert(self, model, output_dir): | |||
| ofa_model = _dynabert_training( | |||
| self, ofa_model, model, teacher_model, train_dataloader, eval_dataloader, args.num_train_epochs | |||
| ) | |||
|
|
|||
| self.reset_optimizer_and_scheduler() | |||
There was a problem hiding this comment.
这里是dynabert的部分，训练完毕后reset 了优化器和学习率，目的是如果后面接入了 qat，防止qat的优化器和学习率是接着dynabert的部分来的而不是自己独立的从头开始。
|
|
||
| input_dir = os.path.dirname(input_prefix) | ||
|
|
||
| paddle.fluid.io.save_inference_model( |
There was a problem hiding this comment.
目前只有这个 API 可以直接使用，新版本的paddle.static.save_inference_model输入需要feed_var，fluid API 只需要feed_var_names，而feed_var_names可以通过上面load_inference_model给出
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Outdated suggestions cannot be applied.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.
PR types
New features
PR changes
APIs
Description
Add Embedding quantization