TinyEngram is an open research project built on Qwen model for exploring the Engram architecture.
active 2026-01-23 → 2026-08-07 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 197 days from 2026-01-23 to 2026-08-07. Pushes: 8 total, peak 2 in a day. Pull requests: 5 total, peak 2 in a day. Issues: 3 total, peak 1 in a day. Comments: 13 total, peak 4 in a day. Stars: 36 total, peak 6 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 |
|---|---|---|---|---|
| Alichua | 17 | 8 | 5 | 4 |
| DDDMUC | 2 | 0 | 0 | 1 |
| matarwapporter | 2 | 0 | 0 | 2 |
| FCY36 | 1 | 0 | 0 | 1 |
| 2211427551 | 1 | 0 | 0 | 1 |
| kendadiggood | 1 | 0 | 0 | 1 |
| wanglamao | 1 | 0 | 0 | 0 |
| coruse123 | 1 | 0 | 0 | 1 |
| Fpw19980724 | 1 | 0 | 0 | 1 |
| rafaelperena | 1 | 0 | 0 | 1 |
| aivolcano | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#1922114275512026-05-09 09:44VRAM usage with Visison-TinyEngram?
- Issue comment#19Alichua2026-05-09 09:22VRAM usage with Visison-TinyEngram?
- Issue#17wanglamao2026-05-08 04:53给所有维护者的忠告：别碰刷星（望回应）
- Issue comment#13rafaelperena2026-05-08 04:47实验1的复现文档好像有错误，看不到。
- Issue comment#12matarwapporter2026-05-08 04:31About scalability to larger base models (e.g., Qwen3-8B)
- Issue comment#6matarwapporter2026-05-08 04:29Discussion: Engram hyperparameter configuration and tuning
- Issue comment#3kendadiggood2026-05-08 04:29about engram vocab size
- Issue#15aivolcano2026-05-02 10:33PLS provide the requirement.txt for setting up the the ENV
- Issue comment#12Alichua2026-04-13 04:30About scalability to larger base models (e.g., Qwen3-8B)
- Issue comment#12DDDMUC2026-04-10 17:21About scalability to larger base models (e.g., Qwen3-8B)
- Issue#13DDDMUC2026-04-06 18:05实验1的复现文档好像有错误，看不到。
- Issue comment#11Alichua2026-03-04 09:57About deepspeed ZeRO-3 training
- Issue comment#11Fpw199807242026-03-04 08:11About deepspeed ZeRO-3 training
- Pull request#9Alichua2026-02-03 09:50
- Pull request#8Alichua2026-02-02 04:11
- Pull request#8Alichua2026-02-02 04:11
- Pull request#7Alichua2026-01-30 09:24
- Pull request#4Alichua2026-01-29 05:22
- Issue comment#3coruse1232026-01-28 07:52about engram vocab size
- Issue comment#3Alichua2026-01-28 04:38about engram vocab size
- Issue comment#3FCY362026-01-28 03:18about engram vocab size
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 36 stars here means stars gained during the window, not the repo's star count.