HQCLIP
Collection
7 items • Updated
Pretrain CLIP-L-14 on VLM-1B using CLIPA.
| Dataset | Performance |
|---|---|
| ImageNet 1k | 0.78628 |
| ImageNet V2 | 0.7132 |
| ImageNet-A | 0.662 |
| ImageNet-O | 0.4085 |
| ImageNet-R | 0.900967 |
| ImageNet Sketch | 0.673643 |
| ObjectNet | 0.716324 |
| IN-shifts | 0.679106 |
| VTAB | 0.604791 |
| MSCOCO | 0.580741 |
| Flickr30k | 0.841 |
| WinoGAViL | 0.509853 |
| Retrieval | 0.643865 |
| Avg. | 0.637904 |
license: apache-2.0
- Downloads last month
- 20
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support