small language models training made easy
active 2024-01-24 → 2025-05-05 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 468 days from 2024-01-24 to 2025-05-05. Pushes: 549 total, peak 27 in a day. Pull requests: 124 total, peak 10 in a day. Issues: 155 total, peak 12 in a day. Comments: 488 total, peak 26 in a day. Stars: 14 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 |
|---|---|---|---|---|
| jettjaniak | 681 | 132 | 41 | 262 |
| jaidhyani | 488 | 249 | 53 | 92 |
| menamerai | 117 | 57 | 12 | 28 |
| joshuawe | 116 | 33 | 5 | 43 |
| siwei-li | 60 | 28 | 4 | 18 |
| SrGonao | 60 | 15 | 3 | 21 |
| transcendingvictor | 47 | 31 | 6 | 5 |
| jannik-brinkmann | 39 | 4 | 0 | 17 |
| woog97 | 1 | 0 | 0 | 1 |
| leycec | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#121jettjaniak2024-05-28 13:06find, implement & document auth solution for hf & wandb
- Issue#152jettjaniak2024-05-28 13:05text dataset is not shuffled before tokenization
- Releasejettjaniak2024-05-28 12:54v0.2
- Releasejettjaniak2024-05-28 12:52v0.1.1
- Pull request#149jettjaniak2024-05-28 12:50
- Pull request#144jettjaniak2024-05-25 13:03
- Issue comment#121jettjaniak2024-05-23 16:58find, implement & document auth solution for hf & wandb
- Issue#151jettjaniak2024-05-23 16:40add progress bar in `scripts/tokenize_dataset.py`
- Issue comment#121jettjaniak2024-05-23 10:10find, implement & document auth solution for hf & wandb
- Issue#124jettjaniak2024-05-22 16:29clean up repo
- Issue#150jettjaniak2024-05-22 10:44speedup estimate_loss
- Issue#125jettjaniak2024-05-22 09:47token selector not showing up
- Issue#126jettjaniak2024-05-22 09:46`pip install -r requirements.txt` shouldn't install delphi
- Pull request#149jettjaniak2024-05-22 09:45
- Pull request#98jettjaniak2024-05-22 09:26
- Issue comment#142jettjaniak2024-05-22 09:17add readme_path to config for HF model cards
- Issue#147jettjaniak2024-05-21 13:29save/upload the tokenizer with the model
- Pull request#148jettjaniak2024-05-21 13:28
- Pull request#148jettjaniak2024-05-21 11:44
- Issue#147jettjaniak2024-05-20 21:52save/upload the tokenizer with the model
- Issue#146jettjaniak2024-05-20 15:40HF LFS upload SSL error caused a crash
- Issue comment#144jettjaniak2024-05-20 15:03fix problem with attention_size
- Issue#146jettjaniak2024-05-20 12:36HF LFS upload SSL error caused a crash
- Issue#138jettjaniak2024-05-20 11:32add performance tests
- Pull request#140jettjaniak2024-05-20 11:32
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 14 stars here means stars gained during the window, not the repo's star count.