Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.
active 2024-05-01 → 2026-04-17 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 717 days from 2024-05-01 to 2026-04-17. Pushes: 5 total, peak 2 in a day. Pull requests: 4 total, peak 3 in a day. Issues: 16 total, peak 2 in a day. Comments: 22 total, peak 7 in a day. Stars: 120 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 |
|---|---|---|---|---|
| jperez999 | 8 | 4 | 4 | 0 |
| rnyak | 6 | 0 | 0 | 3 |
| shaun0927 | 6 | 0 | 0 | 4 |
| copy-pr-bot[bot] | 5 | 0 | 0 | 5 |
| mvidela31 | 5 | 0 | 0 | 2 |
| karunaahuja | 5 | 0 | 0 | 4 |
| dpendleton22 | 3 | 0 | 0 | 1 |
| hk63560892 | 2 | 0 | 0 | 1 |
| korchi | 1 | 0 | 0 | 0 |
| lmatejka | 1 | 0 | 0 | 1 |
| PreyumKr | 1 | 0 | 0 | 0 |
| SinnerSS | 1 | 0 | 0 | 0 |
| abhilashadavi | 1 | 0 | 0 | 0 |
| maciekrtb | 1 | 0 | 0 | 0 |
| github-actions[bot] | 1 | 1 | 0 | 0 |
| review-notebook-app[bot] | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#816shaun09272026-04-17 05:17Fix TypeError in Model.load on Python 3.9+
- Issue comment#819shaun09272026-04-17 04:39Restore default factory on `Head._task_weights`
- Issue comment#817shaun09272026-04-17 04:39Fix TypeError in Head.build when body lacks output_size
- Issue comment#819copy-pr-bot[bot]2026-04-17 04:16Restore default factory on `Head._task_weights`
- Issue comment#817copy-pr-bot[bot]2026-04-17 04:10Fix TypeError in Head.build when body lacks output_size
- Issue comment#816copy-pr-bot[bot]2026-04-17 04:09Fix TypeError in Model.load on Python 3.9+
- Issue comment#806shaun09272026-04-17 04:08[BUG] `load_model_trainer_states_from_checkpoint()` function is broken
- Issue#815shaun09272026-04-17 04:08[SECURITY] `torch.load()` called without `weights_only=True` under `torch>=1.0` pin
- Issue#810shaun09272026-04-17 04:06[BUG] `Model.load` raises TypeError on Python 3.9+ (parameterized generic in isinstance)
- Issue comment#809copy-pr-bot[bot]2026-03-12 04:49Fix scaler
- Issue comment#808review-notebook-app[bot]2026-03-12 04:35Fix scaler
- Issue comment#805copy-pr-bot[bot]2025-12-04 22:11fixed scaler load route
- Pull request#805jperez9992025-12-04 22:11
- Pull request#805jperez9992025-12-04 22:11
- Pull request#805jperez9992025-12-04 22:11
- Issue comment#785rnyak2025-08-13 16:56[QST] Example notebook for PostContextFusion using embedding feature
- Issue#785rnyak2025-08-13 16:56[QST] Example notebook for PostContextFusion using embedding feature
- Issue#796mvidela312025-01-09 02:09[DOC] Pre-trained Embeddings Usage
- Issue#795SinnerSS2024-12-27 16:44[BUG]
- Issue comment#793mvidela312024-12-24 20:41[BUG] Cannot install transformers4rec through pip
- Issue#793mvidela312024-12-24 20:41[BUG] Cannot install transformers4rec through pip
- Issue comment#794mvidela312024-12-24 20:39[QST] Unable to reproduce the getting-started tutorial on AWS SageMaker
- Issue#794mvidela312024-12-24 20:39[QST] Unable to reproduce the getting-started tutorial on AWS SageMaker
- Issue#792maciekrtb2024-10-28 23:32[QST] Categorifying nested lists in NVTabular and transformers4rec
- Issue comment#770lmatejka2024-09-19 20:21Model is not generating accurate recommandations [QST]
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 120 stars here means stars gained during the window, not the repo's star count.