Tool for converting LLMs from uni-directional to bi-directional for tasks like classification and sentence embeddings. Compatible with 🤗 transformers.
active 2024-03-17 → 2026-03-09 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 723 days from 2024-03-17 to 2026-03-09. Pushes: 15 total, peak 6 in a day. Pull requests: 8 total, peak 4 in a day. Issues: 8 total, peak 1 in a day. Comments: 15 total, peak 5 in a day. Stars: 34 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 |
|---|---|---|---|---|
| SeanLee97 | 35 | 15 | 8 | 11 |
| qinglongheu | 4 | 0 | 0 | 2 |
| KoichiYasuoka | 3 | 0 | 0 | 1 |
| wmkai | 1 | 0 | 0 | 0 |
| benjamin-kroeger | 1 | 0 | 0 | 0 |
| SGidentification | 1 | 0 | 0 | 1 |
| WorldHellow | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#16SeanLee972024-12-12 02:46FA2 and rotary positional embeddings
- Pull request#15SeanLee972024-12-12 02:41
- Issue comment#15SeanLee972024-12-12 02:41feature(zaobao): for latest transformer Qwen2 model
- Issue#16benjamin-kroeger2024-12-07 08:08FA2 and rotary positional embeddings
- Issue#14WorldHellow2024-06-27 11:05Query Regarding Masking
- Issue comment#14SeanLee972024-06-27 05:06Query Regarding Masking
- Issue#11qinglongheu2024-05-27 03:08encounter a debug when running mistral model
- Issue comment#11SeanLee972024-05-25 08:24encounter a debug when running mistral model
- Issue comment#11qinglongheu2024-05-25 07:46encounter a debug when running mistral model
- Issue comment#11qinglongheu2024-05-25 07:41encounter a debug when running mistral model
- Issue comment#11SeanLee972024-05-25 07:16encounter a debug when running mistral model
- Pull request#12SeanLee972024-05-25 07:05
- Issue comment#11SeanLee972024-05-25 02:23encounter a debug when running mistral model
- Issue#11qinglongheu2024-05-25 01:48encounter a debug when running mistral model
- Issue comment#8SeanLee972024-05-17 03:12Llama-2-13b
- Issue comment#8SGidentification2024-05-16 10:15Llama-2-13b
- Issue comment#10SeanLee972024-05-16 07:18Example for sequence classification
- Issue#8SeanLee972024-05-01 06:35Llama-2-13b
- Pull request#9SeanLee972024-04-27 08:13
- Issue comment#8SeanLee972024-04-24 01:51Llama-2-13b
- Issue#7wmkai2024-04-21 22:47What's the prompt for NER task?
- Issue comment#3KoichiYasuoka2024-04-07 08:23Variable classifier_dropout
- Issue#3KoichiYasuoka2024-04-07 08:23Variable classifier_dropout
- Pull request#5SeanLee972024-04-07 03:29
- Pull request#5SeanLee972024-04-07 03:29
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 34 stars here means stars gained during the window, not the repo's star count.