[ICCV2023] TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
active 2024-01-21 → 2026-03-22 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 792 days from 2024-01-21 to 2026-03-22. Pushes: 2 total, peak 1 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 16 total, peak 2 in a day. Comments: 33 total, peak 4 in a day. Stars: 112 total, peak 21 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 |
|---|---|---|---|---|
| wkcn | 28 | 2 | 0 | 19 |
| alexandsunny | 6 | 0 | 0 | 4 |
| willswordh | 5 | 0 | 0 | 5 |
| loserking111 | 4 | 0 | 0 | 3 |
| gaoyifanginpg | 3 | 0 | 0 | 1 |
| llbbl | 1 | 0 | 1 | 0 |
| Roy7754321 | 1 | 0 | 0 | 0 |
| HuazhangHu | 1 | 0 | 0 | 0 |
| hyeinhyun | 1 | 0 | 0 | 1 |
| adi070701 | 1 | 0 | 0 | 0 |
| peymanrostami | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#10wkcn2025-09-04 02:18feat: Add comprehensive Python testing infrastructure with Poetry
- Pull request#10llbbl2025-09-01 19:55
- Issue#9peymanrostami2025-06-10 15:45dynamics of the values of lambda1 and lambda2
- Issue#8wkcn2025-01-07 07:34weight of model
- Issue#7wkcn2025-01-07 07:34推理时显存泄漏的问题
- Issue comment#8wkcn2024-12-19 15:27weight of model
- Issue#8Roy77543212024-12-19 05:50weight of model
- Issue comment#7wkcn2024-12-13 23:51推理时显存泄漏的问题
- Issue comment#7wkcn2024-12-13 23:13推理时显存泄漏的问题
- Issue#7HuazhangHu2024-12-09 11:51推理时显存泄漏的问题
- Issue#6wkcn2024-10-29 01:33Tiny CLIP performance not upto mark
- Issue#6adi0707012024-10-15 09:43Tiny CLIP performance not upto mark
- Issue#5gaoyifanginpg2024-10-15 08:27inference error with TinyCLIP-auto-ViT-45M-32-Text-18M-LAIONYFCC400M.pt
- Issue comment#5gaoyifanginpg2024-10-15 08:27inference error with TinyCLIP-auto-ViT-45M-32-Text-18M-LAIONYFCC400M.pt
- Issue comment#5wkcn2024-10-15 01:51inference error with TinyCLIP-auto-ViT-45M-32-Text-18M-LAIONYFCC400M.pt
- Issue#5gaoyifanginpg2024-10-14 13:08inference error with TinyCLIP-auto-ViT-45M-32-Text-18M-LAIONYFCC400M.pt
- Issue#4wkcn2024-09-14 01:00Does model weight convertible between HF model weight and Open_clip model weight?
- Issue comment#4hyeinhyun2024-09-13 08:35Does model weight convertible between HF model weight and Open_clip model weight?
- Issue comment#4wkcn2024-09-03 01:39Does model weight convertible between HF model weight and Open_clip model weight?
- Issue#3wkcn2024-09-02 06:33I want to replace the clip model weights with Tinyclip model weights to initialize, how should I change the network architecture?
- Issue comment#3wkcn2024-07-19 14:31I want to replace the clip model weights with Tinyclip model weights to initialize, how should I change the network architecture?
- Issue comment#3willswordh2024-07-18 00:14I want to replace the clip model weights with Tinyclip model weights to initialize, how should I change the network architecture?
- Issue comment#3wkcn2024-07-17 08:43I want to replace the clip model weights with Tinyclip model weights to initialize, how should I change the network architecture?
- Issue comment#3willswordh2024-07-17 07:32I want to replace the clip model weights with Tinyclip model weights to initialize, how should I change the network architecture?
- Issue comment#3wkcn2024-07-17 06:17I want to replace the clip model weights with Tinyclip model weights to initialize, how should I change the network architecture?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 112 stars here means stars gained during the window, not the repo's star count.