Model card
DeiT-B Distilled.
Metaopen-source86M paramsVision TransformerApache 2.0
85.2% on ImageNet. Trained on ImageNet-1K only.
§ 02 · Benchmarks
Every benchmark DeiT-B Distilled has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | CIFAR-10 | Computer Vision · Image Classification | accuracy | 99.1% | #4 | — | source ↗ |
| 02 | ImageNet-1K | Computer Vision · Image Classification | top-1-accuracy | 85.2% | #11 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where DeiT-B Distilled actually performs.
§ 05 · Related models
Other Meta models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
meta-research
2
results
0 of 2 rows marked verified.