LLM2CLIP makes SOTA pretrained CLIP model more SOTA ever.
active 2025-03-19 → 2026-05-09 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 417 days from 2025-03-19 to 2026-05-09. Pushes: 4 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 13 total, peak 2 in a day. Comments: 17 total, peak 3 in a day. Stars: 65 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 |
|---|---|---|---|---|
| raytrun | 8 | 0 | 0 | 8 |
| Yif-Yang | 4 | 4 | 0 | 0 |
| konioy | 4 | 0 | 0 | 0 |
| mengcius | 2 | 0 | 0 | 1 |
| LKELN | 2 | 0 | 0 | 1 |
| supersuper32 | 2 | 0 | 0 | 1 |
| xiaoxing2001 | 2 | 0 | 0 | 1 |
| ly1998117 | 2 | 0 | 0 | 1 |
| wswaq | 1 | 0 | 0 | 1 |
| zxqing01 | 1 | 0 | 0 | 0 |
| StuHude | 1 | 0 | 0 | 1 |
| Justin-Regef | 1 | 0 | 0 | 0 |
| Gbone3176 | 1 | 0 | 0 | 1 |
| msoltanisarvestani | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#63Gbone31762026-02-03 01:56epoch setting for the CC-Finetune text supervised contrastive training stage
- Issue#62ly19981172026-01-27 08:27Question about auto_map usage in config.json for LlamaEncoderModel
- Issue comment#21raytrun2026-01-23 16:22Confusions about original clip text-encoder context window length
- Issue comment#21ly19981172025-09-30 09:00Confusions about original clip text-encoder context window length
- Issue#61xiaoxing20012025-07-24 11:26训练代码
- Issue#61xiaoxing20012025-07-19 08:19训练代码
- Issue#59konioy2025-07-07 11:54about "attn_implementation"
- Issue#59konioy2025-07-07 09:10about "attn_implementation"
- Issue comment#57xiaoxing20012025-06-27 07:09关于数据
- Issue comment#57raytrun2025-06-27 03:55关于数据
- Issue comment#57raytrun2025-06-27 03:51关于数据
- Issue comment#57raytrun2025-06-26 07:45关于数据
- Issue#57xiaoxing20012025-06-26 07:26关于数据
- Issue comment#56raytrun2025-06-25 04:53Where can I download this file?
- Issue#55zxqing012025-06-11 12:14How do I replace the evaclip?
- Issue comment#54supersuper322025-06-09 06:38How to load LLM2CLIP-EVA02-L-14-336 model?
- Issue comment#51mengcius2025-06-09 03:48about siglip2 and llama3.1-8b
- Issue#54supersuper322025-06-09 02:29What is the "LLM2Vec-Meta-Llama-3-8B-Instruct-mntp"?
- Issue#53konioy2025-06-05 02:10issue about cc3m_SnL
- Issue comment#53wswaq2025-06-04 13:52issue about cc3m_SnL
- Issue comment#51raytrun2025-06-03 08:02about siglip2 and llama3.1-8b
- Issue comment#47msoltanisarvestani2025-05-30 08:34Packages are incomatible
- Issue comment#48raytrun2025-05-29 09:59how to create our own dataset to finetune the model?
- Issue comment#47raytrun2025-05-29 09:49Packages are incomatible
- Issue#52Justin-Regef2025-05-28 12:03Training Vision Encoder from scractch
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 65 stars here means stars gained during the window, not the repo's star count.