Differentially-private transformers using HuggingFace and Opacus
active 2023-08-16 → 2025-10-21 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 798 days from 2023-08-16 to 2025-10-21. Pushes: 13 total, peak 5 in a day. Pull requests: 8 total, peak 5 in a day. Issues: 18 total, peak 2 in a day. Comments: 35 total, peak 3 in a day. Stars: 52 total, peak 3 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| huseyinatahaninan | 22 | 3 | 3 | 13 |
| wulu473 | 14 | 9 | 2 | 1 |
| edifice1989 | 9 | 0 | 0 | 5 |
| Ethan-Chen-plus | 9 | 0 | 0 | 6 |
| fangyiyu | 4 | 0 | 0 | 1 |
| dependabot[bot] | 3 | 1 | 2 | 0 |
| dooohow | 2 | 0 | 0 | 2 |
| DSW2001 | 2 | 0 | 0 | 0 |
| BigfufuOuO | 2 | 0 | 0 | 2 |
| JiuJiaozgmzb | 2 | 0 | 0 | 1 |
| fespadea | 1 | 0 | 0 | 0 |
| Liuzzyg | 1 | 0 | 0 | 1 |
| andreatgretel | 1 | 0 | 0 | 0 |
| ForeverZHHY | 1 | 0 | 0 | 1 |
| stevenL-1047 | 1 | 0 | 0 | 0 |
| lmarchyok | 1 | 0 | 0 | 1 |
| mahrokh3409 | 1 | 0 | 0 | 0 |
| matthieumeeus | 1 | 0 | 1 | 0 |
| MarkDeng1 | 1 | 0 | 0 | 0 |
| ooolivia2333 | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#55ForeverZHHY2025-10-21 16:11PrivacyEngineCallback still referenced in README despite being replaced with DPCallback
- Pull request#57matthieumeeus2025-07-10 09:48
- Issue comment#53BigfufuOuO2025-04-25 03:15How can I load model after lora fine tune？
- Issue comment#45BigfufuOuO2025-04-21 05:36Integrating opacus with huggingface
- Issue comment#45huseyinatahaninan2025-02-22 16:43Integrating opacus with huggingface
- Issue comment#45dooohow2025-02-22 10:25Integrating opacus with huggingface
- Issue comment#48dooohow2025-02-22 09:29Error for finetuning `/microsoft/analysing_pii_leakage/` for DP-based configuration
- Issue#56edifice19892024-12-18 06:34disable_dp hangs the training process
- Issue comment#56edifice19892024-12-16 00:21disable_dp hangs the training process
- Issue comment#56edifice19892024-12-15 06:48disable_dp hangs the training process
- Issue comment#56huseyinatahaninan2024-12-14 21:20disable_dp hangs the training process
- Issue comment#56edifice19892024-12-14 06:52disable_dp hangs the training process
- Issue#56edifice19892024-12-11 23:50disable_dp hangs the training process
- Issue#55fespadea2024-10-29 01:25PrivacyEngineCallback still referenced in README despite being replaced with DPCallback
- Issue comment#54JiuJiaozgmzb2024-10-24 01:09yelp数据集
- Issue#54JiuJiaozgmzb2024-10-22 07:41yelp数据集
- Issue#53DSW20012024-10-12 03:26How can I load model after lora fine tune？
- Issue#52DSW20012024-10-03 19:28fine-tune-dp runtime error in sample-level-dp of examples files
- Issue comment#51edifice19892024-09-30 06:08example author-level-dp error
- Issue#51edifice19892024-09-30 06:08example author-level-dp error
- Issue comment#51edifice19892024-09-30 06:08example author-level-dp error
- Issue comment#51huseyinatahaninan2024-09-29 15:41example author-level-dp error
- Issue#51edifice19892024-09-29 07:14example author-level-dp error
- Issue#49stevenL-10472024-08-14 02:41Error for fine-tuning llama2-7B using dp-transformers
- Issue#48mahrokh34092024-08-10 23:51Error for finetuning `/microsoft/analysing_pii_leakage/` for DP-based configuration
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 52 stars here means stars gained during the window, not the repo's star count.