MobileVLM-1.7B (w/ LoRA, w/ extra data)

Reported on 3 benchmarks across 2 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Referring expression generationonColonINST-v1 (Unseen)
Accuray· 2023-12-28
78.03
best: 80.18 (ColonGPT (w/ LoRA, w/o extra data))
SOTA
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices arXiv:2312.16886
Image ClassificationonColonINST-v1 (Unseen)
Accuray· 2023-12-28
80.44
best: 83.24 (ColonGPT (w/ LoRA, w/o extra data))
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices arXiv:2312.16886
Referring expression generationonColonINST-v1 (Seen)
Accuray· 2023-12-28
97.87
best: 99.96 (ColonGPT (w/ LoRA, w/o extra data))
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices arXiv:2312.16886