Merlin Models is a collection of deep learning recommender system model reference implementations
active 2024-03-31 → 2025-11-23 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 603 days from 2024-03-31 to 2025-11-23. Pushes: 2 total, peak 1 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 3 total, peak 1 in a day. Comments: 14 total, peak 3 in a day. Stars: 35 total, peak 1 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 |
|---|---|---|---|---|
| hkristof03 | 5 | 0 | 0 | 4 |
| CarloNicolini | 4 | 0 | 0 | 4 |
| ibraheemalayan | 3 | 0 | 1 | 2 |
| sararb | 2 | 0 | 0 | 2 |
| jhnealand | 2 | 0 | 0 | 1 |
| github-actions[bot] | 2 | 2 | 0 | 0 |
| breadbread1984 | 1 | 0 | 0 | 0 |
| copy-pr-bot[bot] | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#1248hkristof032025-06-18 12:47[BUG] - Changing the embedding dimensions of the schema has no effect on the subsequent model architecture
- Issue#1245breadbread19842024-11-27 01:38[QST] What is the proper way to load checkpoint to merlin.models.torch.DLRMModel
- Issue comment#1243sararb2024-07-04 22:21[QST] Questions about topk_model.evaluate()
- Issue comment#1229sararb2024-07-04 22:15[QST] How to use negative sampling with ranking models ?
- Issue comment#1242hkristof032024-06-29 07:46[BUG] ModelCheckpoint Callback results in an error due to unsupported overwrite=True parameter
- Issue comment#1033CarloNicolini2024-06-28 22:22Benchmark, improve and document mixed precision (AMP) support in Models
- Issue comment#1013CarloNicolini2024-06-28 17:26[QST] How to use pretrained embeddings as features in DLRM?
- Issue comment#1242hkristof032024-06-27 19:20[BUG] ModelCheckpoint Callback results in an error due to unsupported overwrite=True parameter
- Issue comment#1013CarloNicolini2024-06-10 23:56[QST] How to use pretrained embeddings as features in DLRM?
- Issue comment#1230CarloNicolini2024-06-07 18:25[BUG] when the model is loaded and saved again, the argument names disappear (become 'args_0, args_0_1 etc)
- Issue comment#1239hkristof032024-06-07 07:33[QST] How to get candidate features after using pre-trained embedding tables?
- Issue comment#1239jhnealand2024-06-06 23:59[QST] How to get candidate features after using pre-trained embedding tables?
- Issue#1241jhnealand2024-06-04 06:08[QST] How to deploy model using Pretrain Embeddings with EmbeddingOperator in Triton
- Issue comment#1013hkristof032024-06-01 11:59[QST] How to use pretrained embeddings as features in DLRM?
- Issue comment#1238copy-pr-bot[bot]2024-05-04 12:44Fix issue #1226
- Pull request#1238ibraheemalayan2024-05-04 12:44
- Issue comment#1226ibraheemalayan2024-05-04 12:40[BUG] Error with prepare_aliccp()
- Issue comment#1226ibraheemalayan2024-05-04 12:32[BUG] Error with prepare_aliccp()
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 35 stars here means stars gained during the window, not the repo's star count.