microsoft/dp-transformers

View on GitHub

Differentially-private transformers using HuggingFace and Opacus

Stars: 149
Forks: 33
Open beginner issues: 0
Indexed issues: 14
Avg merge: 22h 6m
Merged PRs (30d): 1

Dominant language: Python
License: MIT
Last GitHub push: Aug 24, 2026
Latest indexed: Sep 19, 2026
Contributing guide: No contributing guide
Code of conduct: Code of conduct
Beginner labels: No beginner labels indexed

Beginner friendly Everything

Open All

14 open issues indexed

PrivacyEngineCallback still referenced in README despite being replaced with DPCallback Open

Difficulty 1/5 Under an hour Newbie friendliness 65/100

microsoft/dp-transformers#55 · 1 comment · Opened Oct 29, 2024
yelp数据集 Open

Difficulty 1/5 Under an hour Newbie friendliness 25/100

microsoft/dp-transformers#54 · 1 comment · Opened Oct 22, 2024
How can I load model after lora fine tune？ Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

microsoft/dp-transformers#53 · Opened Oct 12, 2024
fine-tune-dp runtime error in sample-level-dp of examples files Open

Difficulty 3/5 1-2 days Newbie friendliness 32/100

microsoft/dp-transformers#52 · 1 comment · Opened Oct 3, 2024
Error for fine-tuning llama2-7B using dp-transformers Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

microsoft/dp-transformers#49 · 1 comment · Opened Aug 14, 2024
Error for finetuning `/microsoft/analysing_pii_leakage/` for DP-based configuration Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

microsoft/dp-transformers#48 · 1 comment · Opened Aug 10, 2024
Gradients haven't been cleared since the last optimizer step. In order to obtain privacy guarantees you must call optimizer.zero_grad()on each step Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

microsoft/dp-transformers#47 · 1 comment · Opened Jul 19, 2024
No module named 'dp_transformers.layers' Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

microsoft/dp-transformers#46 · 1 comment · Opened Jun 28, 2024
Integrating opacus with huggingface Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

microsoft/dp-transformers#45 · 6 comments · Opened Jun 13, 2024
LR scheduler does not work properly due to AcceleratedOptimizer Open

Difficulty 3/5 1-2 days Newbie friendliness 45/100

microsoft/dp-transformers#43 · 2 comments · Opened Apr 26, 2024
`DataCollatorForPrivateCausalLanguageModeling` hardcoded to `mlm=False` Open

Difficulty 4/5 3-5 days Newbie friendliness 30/100

microsoft/dp-transformers#42 · 1 comment · Opened Apr 25, 2024
Cannot import name 'convert_gpt2_attention_to_lora' from 'dp_transformers.module_modification' Open

Difficulty 3/5 1-2 days Newbie friendliness 42/100

microsoft/dp-transformers#38 · 1 comment · Opened Nov 4, 2023
Failed to run the example Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

microsoft/dp-transformers#26 · 12 comments · Opened Jul 4, 2023
Typo in the code Open

Difficulty 1/5 Under an hour Newbie friendliness 55/100

microsoft/dp-transformers#19 · Opened Oct 31, 2022

microsoft/dp-transformers

Get new issues in your inbox