Improve: batch size setting and multi GPU inference with SentenceTransformers+DP #53
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
lsz05
reviewed
Aug 9, 2024
tests/embedders/test_dp_sbert.py
Outdated
| OUTPUT_DIM = 128 | ||
|
|
||
|
|
||
| class TestSentenceBertEmbedder: |
There was a problem hiding this comment.
Suggested change
| class TestSentenceBertEmbedder: | |
| class TestDPSentenceBertEmbedder: |
lsz05
reviewed
Aug 9, 2024
|
|
||
| def _add_eos_func(self, text: str | list[str]) -> str | list[str]: | ||
| try: | ||
| eos_token = getattr(self.model.savetokenizer, "eos_token") |
|
起動時 |
はい。pythonで起動してください。 |
lsz05
reviewed
Aug 9, 2024
lsz05
reviewed
Aug 9, 2024
| self.model = self.dp_model.sbert | ||
| if max_seq_length: | ||
| self.model.max_seq_length = max_seq_length | ||
| self.initital_batch_size = batch_size |
There was a problem hiding this comment.
self.initial_batch_sizeが使われていないような気がしますが
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Outdated suggestions cannot be applied.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.
関連する Issue / PR
PR をマージした後の挙動の変化
挙動の変更を達成するために行ったこと
src/jmteb/embedders/base.pyのTextEmbedderに_chunk_sizeという変数を追加し、_chunk_sizeごとにTextEmbedder.encodeを呼ぶように変更src/jmteb/embedders/data_parallel_sbert_embedder.py追加し、sentence-transfermersでpytorchのDataParallelによる複数GPU推論が可能になった。動作確認