[EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs
active 2024-01-31 → 2025-10-29 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 638 days from 2024-01-31 to 2025-10-29. Pushes: 12 total, peak 4 in a day. Pull requests: 5 total, peak 2 in a day. Issues: 19 total, peak 2 in a day. Comments: 30 total, peak 7 in a day. Stars: 245 total, peak 30 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 |
|---|---|---|---|---|
| bys0318 | 29 | 10 | 1 | 18 |
| KaiLv69 | 5 | 0 | 0 | 3 |
| cuichenxu | 4 | 0 | 0 | 1 |
| S1s-Z | 3 | 0 | 0 | 1 |
| mxjmtxrm | 3 | 0 | 0 | 1 |
| guanzhchen | 3 | 0 | 0 | 1 |
| Geaming-CHN | 2 | 0 | 0 | 0 |
| bwanglzu | 2 | 0 | 2 | 0 |
| BitVoyage | 2 | 0 | 0 | 1 |
| davidlvxin | 2 | 1 | 0 | 1 |
| hijkzzz | 1 | 0 | 0 | 1 |
| eltociear | 1 | 0 | 1 | 0 |
| JianxinDong | 1 | 0 | 1 | 0 |
| Neo-Zhangjiajie | 1 | 1 | 0 | 0 |
| Chandler-Bing | 1 | 0 | 0 | 0 |
| YueChenkkk | 1 | 0 | 0 | 1 |
| liuyongjie985 | 1 | 0 | 0 | 1 |
| SefaZeng | 1 | 0 | 0 | 0 |
| mhzn-yn | 1 | 0 | 0 | 0 |
| wplf | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#18bwanglzu2025-01-31 16:44
- Pull request#18bwanglzu2025-01-31 16:37
- Issue#17wplf2025-01-17 06:18请问训练时有没有开启 full recompute？
- Issue#15cuichenxu2025-01-04 08:46可以参考我们的实现：
- Issue#16cuichenxu2025-01-03 03:01重复输出the the the the
- Issue#15cuichenxu2025-01-03 02:59可以参考我们的实现：
- Issue comment#4cuichenxu2025-01-03 02:28AttributeError: 'LlamaForCausalLM' object has no attribute 'chat'
- Issue comment#12YueChenkkk2024-11-09 08:18packing loss 的归一化问题
- Issue comment#13bys03182024-10-27 09:24微调训练问题
- Issue comment#3bys03182024-10-27 09:21关于Packing和 直接Batch的loss区别？
- Issue comment#3hijkzzz2024-10-20 06:52关于Packing和 直接Batch的loss区别？
- Issue#13mhzn-yn2024-09-30 18:46微调训练问题
- Issue comment#12bys03182024-09-05 08:09packing loss 的归一化问题
- Issue#12Chandler-Bing2024-08-27 02:47packing loss 的归一化问题
- Issue#10S1s-Z2024-06-21 06:03Question about ShareGPT data
- Issue comment#10S1s-Z2024-06-21 06:03Question about ShareGPT data
- Issue comment#8bys03182024-06-13 10:58关于packing loss的问题
- Issue comment#8mxjmtxrm2024-06-13 03:47关于packing loss的问题
- Issue comment#10bys03182024-06-12 10:46Question about ShareGPT data
- Issue comment#11bys03182024-06-12 10:45Needel_test CUDA OOM 了应该怎么解决？
- Issue#8mxjmtxrm2024-06-11 09:40关于packing loss的问题
- Issue#11SefaZeng2024-06-11 09:00Needel_test CUDA OOM 了应该怎么解决？
- Issue#10S1s-Z2024-06-08 08:42Question about ShareGPT data
- Issue comment#9guanzhchen2024-06-05 03:09Prediction Results of LongBench-Chat
- Issue#9guanzhchen2024-06-05 03:09Prediction Results of LongBench-Chat
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 245 stars here means stars gained during the window, not the repo's star count.