Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
active 2024-03-02 → 2026-05-20 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 810 days from 2024-03-02 to 2026-05-20. Pushes: 76 total, peak 10 in a day. Pull requests: 10 total, peak 3 in a day. Issues: 19 total, peak 4 in a day. Comments: 32 total, peak 9 in a day. Stars: 223 total, peak 51 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 |
|---|---|---|---|---|
| simran-arora | 64 | 45 | 3 | 11 |
| seyuboglu | 33 | 23 | 4 | 5 |
| axelmagn | 5 | 0 | 2 | 2 |
| lisc110h | 5 | 0 | 0 | 3 |
| benjaminfspector | 4 | 4 | 0 | 0 |
| fakerybakery | 4 | 0 | 0 | 2 |
| jmercat | 3 | 0 | 0 | 1 |
| AlexiaJM | 3 | 0 | 0 | 1 |
| AsadMir10 | 3 | 0 | 0 | 2 |
| Miking98 | 2 | 0 | 0 | 2 |
| mzio | 2 | 2 | 0 | 0 |
| Aaryan0404 | 2 | 2 | 0 | 0 |
| zhouyuan888888 | 2 | 0 | 0 | 1 |
| haileyschoelkopf | 2 | 0 | 0 | 1 |
| xwx1999 | 1 | 0 | 0 | 0 |
| eltociear | 1 | 0 | 1 | 0 |
| mansur20478 | 1 | 0 | 0 | 0 |
| melisa-writer | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#6simran-arora2025-06-06 00:14FYI: HuggingFace Transformers Request
- Issue comment#17Miking982024-11-20 06:55Swiglu Issue
- Issue comment#17Miking982024-11-19 08:12Swiglu Issue
- Issue comment#17AsadMir102024-10-15 12:03Swiglu Issue
- Issue comment#17AsadMir102024-10-07 14:02Swiglu Issue
- Issue comment#16lisc110h2024-09-16 05:07Evaluating a self-trained model from scratch using the LM Evaluation Harness
- Issue#16lisc110h2024-09-16 05:07Evaluating a self-trained model from scratch using the LM Evaluation Harness
- Issue comment#16simran-arora2024-09-16 02:33Evaluating a self-trained model from scratch using the LM Evaluation Harness
- Issue comment#17simran-arora2024-09-16 02:31Swiglu Issue
- Issue comment#16lisc110h2024-09-13 14:16Evaluating a self-trained model from scratch using the LM Evaluation Harness
- Issue#17AsadMir102024-08-02 11:45Swiglu Issue
- Issue comment#15lisc110h2024-06-19 08:00a question, thank you for your reply
- Issue comment#16simran-arora2024-06-08 14:52Evaluating a self-trained model from scratch using the LM Evaluation Harness
- Issue#16lisc110h2024-06-07 09:05Evaluating a self-trained model from scratch using the LM Evaluation Harness
- Issue#15simran-arora2024-05-15 04:28a question, thank you for your reply
- Issue comment#13simran-arora2024-05-15 04:28How to run prefill phase of inference benchmark?
- Issue#13simran-arora2024-05-15 04:28How to run prefill phase of inference benchmark?
- Issue comment#15zhouyuan8888882024-05-09 06:53a question, thank you for your reply
- Issue comment#15simran-arora2024-05-09 06:50a question, thank you for your reply
- Issue#15zhouyuan8888882024-05-09 06:30a question, thank you for your reply
- Issue#14simran-arora2024-05-03 00:33Upstreaming SWDE, FDA, and Squad-completion to Eval Harness
- Issue comment#14simran-arora2024-04-20 19:34Upstreaming SWDE, FDA, and Squad-completion to Eval Harness
- Issue comment#14haileyschoelkopf2024-04-08 00:31Upstreaming SWDE, FDA, and Squad-completion to Eval Harness
- Issue comment#14simran-arora2024-04-07 21:46Upstreaming SWDE, FDA, and Squad-completion to Eval Harness
- Issue#14haileyschoelkopf2024-04-07 17:24Upstreaming SWDE, FDA, and Squad-completion to Eval Harness
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 223 stars here means stars gained during the window, not the repo's star count.