Add node exclusion for benchmark suite#284
Merged
Merged
Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. |
mfuntowicz
approved these changes
Jul 12, 2022
JingyaHuang
added a commit
that referenced
this pull request
Jul 13, 2022
author JingyaHuang <huang_jingya@outlook.com> 1657578205 +0000 committer JingyaHuang <huang_jingya@outlook.com> 1657721065 +0000 Merge main Fix docstring Fix condition Update glue example Update ner example Update qa example Merge with main add to run_qa when loading dataset Merge with main (#293) * merge with main Correct bug in post-processing benchmark/eval (#278) * correct bug in text processing * update comment Co-authored-by: Felix Marty <felix@huggingface.co> Fix the number of layer to the decoder ones when creating the past key values outputs (#279) Update index.mdx (#235) Fix ⭐ to display ⭐ symbol Remove duplicated key in supported pipeline task (#281) ORT-OPTIMUM (#229) * copy language-modeling/run_mlm.py from HF repo * using ORTTrainer instead of Trainer * remove some unused arg in function to make it could run with ORTTrainer Co-authored-by: zhijxu <zhijxu> Fix documentation for ORTModelForImageClassification (#283) add preprocessors for benchmark (#284) Co-authored-by: Felix Marty <felix@huggingface.co> Add the possibility to use an authentication token when loading the calibration dataset (#289) * Add the possibility to use an authentication token when loading the calibration dataset * Remove " in docstring Co-authored-by: Ella Charlaix <80481427+echarlaix@users.noreply.github.com> Co-authored-by: Ella Charlaix <80481427+echarlaix@users.noreply.github.com>
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Up to now we did not support node exclusion for the benchmark suite. Here's a first rough support, but I expect it to be extended, typically if we do some kind of sensitivity analysis (be it here public or in autoquantize).