Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Dynamic Quantization on BERT notebook - huggingface transformer version #1114

Closed
lambdaofgod opened this issue Aug 9, 2020 · 1 comment · Fixed by #2369
Closed

Dynamic Quantization on BERT notebook - huggingface transformer version #1114

lambdaofgod opened this issue Aug 9, 2020 · 1 comment · Fixed by #2369
Assignees
@TheMemoryDealer
Labels
docathon-h1-2023 A label for the docathon in H1 2023 easy quantization Issues relating to quantization tutorials

Comments

@lambdaofgod
Copy link

🐛 Bug

The notebook for Dynamic Quantization on BERT should use fixed version of huggingface/transformers, I've tried and it works with transformers==2.0.0

Withouth this change it gives error in section 3.2:

TypeError: glue_convert_examples_to_features() got an unexpected keyword argument 'pad_on_left'
@holly1238 holly1238 added the quantization Issues relating to quantization tutorials label Jul 27, 2021
@svekars svekars added easy docathon-h1-2023 A label for the docathon in H1 2023 labels May 31, 2023
@TheMemoryDealer
Copy link
Contributor

TheMemoryDealer commented May 31, 2023 •
edited
Loading

/assigntome

TheMemoryDealer added a commit to TheMemoryDealer/tutorials that referenced this issue May 31, 2023
@TheMemoryDealer
Update dynamic_quantization_bert_tutorial.rst
aafff46 
As per suggestion in pytorch#1114
@TheMemoryDealer TheMemoryDealer mentioned this issue May 31, 2023
Merged
4 tasks
svekars pushed a commit that referenced this issue May 31, 2023
@TheMemoryDealer
Update dynamic_quantization_bert_tutorial.rst (#2369)
dfc6aa2 
As per suggestion in #1114
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@TheMemoryDealer TheMemoryDealer

Labels
docathon-h1-2023 A label for the docathon in H1 2023 easy quantization Issues relating to quantization tutorials
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Update dynamic_quantization_bert_tutorial.rst TheMemoryDealer/tutorials
4 participants
@lambdaofgod @svekars @TheMemoryDealer @holly1238