Model card
InternViT-6B (InternVL).
OpenGVLabopen-source6B paramsInternViT vision encoder (InternVL family)
Vision encoder component of InternVL. 6B params, patch14, 224px. Pre-trained with CLIP-style contrastive loss on LAION-type data, evaluated with linear classifier. CVPR 2024 Oral. Paper: arxiv:2312.14238.
§ 01 · Benchmarks
Every benchmark InternViT-6B (InternVL) has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | ImageNet | Computer Vision · Image Classification | top-1-accuracy | 88.2% | #5 | 2024-06-01 | source ↗ |
| 02 | ImageNet-1K | Computer Vision · Image Classification | top-1-accuracy | 88.2% | #7 | — | 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.
§ 02 · Strengths by area
Where InternViT-6B (InternVL) actually performs.
§ 03 · Papers
1 paper with results for InternViT-6B (InternVL).
- 2023-12-21· Computer Vision· 1 result
InternVL: Scaling up Vision Foundation Models
Chen et al.
§ 05 · Sources & freshness
Where these numbers come from.
codesota-editorial
1
result
cvpr-2024
1
result
1 of 2 rows marked verified.