The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".
active 2024-10-16 → 2026-04-23 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 555 days from 2024-10-16 to 2026-04-23. Pushes: 17 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 9 total, peak 2 in a day. Comments: 11 total, peak 5 in a day. Stars: 75 total, peak 9 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 |
|---|---|---|---|---|
| Shwai-He | 21 | 14 | 0 | 3 |
| s1ghhh | 4 | 3 | 0 | 1 |
| mathCrazyy | 4 | 0 | 0 | 4 |
| sunkun1997 | 3 | 0 | 0 | 1 |
| kimwin2 | 2 | 0 | 0 | 2 |
| vicky157 | 1 | 0 | 0 | 0 |
| Luo-Zhongwei | 1 | 0 | 0 | 0 |
| Acedev003 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#16Shwai-He2025-10-01 17:55does not appear to be a Python project: neither 'setup.py' nor 'pyproject.toml' found
- Issue#16Luo-Zhongwei2025-06-02 23:21does not appear to be a Python project: neither 'setup.py' nor 'pyproject.toml' found
- Issue#13vicky1572024-12-04 01:41eval issue
- Issue comment#12mathCrazyy2024-12-03 05:55how can I run benchmark_speed.sh correctly?
- Issue comment#12mathCrazyy2024-12-03 03:06how can I run benchmark_speed.sh correctly?
- Issue comment#12mathCrazyy2024-12-03 03:04how can I run benchmark_speed.sh correctly?
- Issue comment#12Shwai-He2024-12-03 02:54how can I run benchmark_speed.sh correctly?
- Issue comment#12mathCrazyy2024-12-03 02:24how can I run benchmark_speed.sh correctly?
- Issue#8Shwai-He2024-11-21 00:08Can not find "reserved_layers.json"
- Issue#6Shwai-He2024-11-21 00:08how can i run the benchmark_lm_eval.sh?
- Issue#5Shwai-He2024-11-17 20:18loading the saved pruned model
- Issue comment#6kimwin22024-11-12 02:26how can i run the benchmark_lm_eval.sh?
- Issue comment#7s1ghhh2024-11-11 01:03Implementing this on other models apart from LLaMa and Mistral
- Issue#7Acedev0032024-11-10 17:40Implementing this on other models apart from LLaMa and Mistral
- Issue comment#6Shwai-He2024-11-10 04:44how can i run the benchmark_lm_eval.sh?
- Issue comment#6kimwin22024-11-08 01:30how can i run the benchmark_lm_eval.sh?
- Issue#4sunkun19972024-10-22 02:24How to assess the importance of the module?
- Issue comment#4sunkun19972024-10-22 02:24How to assess the importance of the module?
- Issue comment#4Shwai-He2024-10-19 15:49How to assess the importance of the module?
- Issue#4sunkun19972024-10-19 07:36How to assess the importance of the module?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 75 stars here means stars gained during the window, not the repo's star count.