Codesota · Models · InternViT-6B (InternVL)OpenGVLab2 results · 2 benchmarks
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.

#BenchmarkArea · TaskMetricValueRankDateSource
01ImageNetComputer Vision · Image Classificationtop-1-accuracy88.2%#5/102024-06-01source ↗
02ImageNet-1KComputer Vision · Image Classificationtop-1-accuracy88.2%#7/20source ↗
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.

Computer Vision
2
benchmarks
avg rank #6.0
§ 03 · Papers

1 paper with results for InternViT-6B (InternVL).

  1. 2023-12-21· Computer Vision· 1 result

    InternVL: Scaling up Vision Foundation Models

    Chen et al.
§ 04 · Related models

Other OpenGVLab models scored on Codesota.

InternVL3 14B
1 result
§ 05 · Sources & freshness

Where these numbers come from.

codesota-editorial
1
result
cvpr-2024
1
result
1 of 2 rows marked verified.