Bunny-v1.0-3B (w/ LoRA, w/o extra data)

Reported on 3 benchmarks across 2 tasks · 1 paper

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

Computer Vision3 results

Image ClassificationonColonINST-v1 (Unseen)
Accuray· 2024-02-18
75.5
best: 83.24 (ColonGPT (w/ LoRA, w/o extra data))
Efficient Multimodal Learning from Data-centric Perspective arXiv:2402.11530
Referring expression generationonColonINST-v1 (Unseen)
Accuray· 2024-02-18
69.45
best: 80.18 (ColonGPT (w/ LoRA, w/o extra data))
Efficient Multimodal Learning from Data-centric Perspective arXiv:2402.11530
Referring expression generationonColonINST-v1 (Seen)
Accuray· 2024-02-18
96.61
best: 99.96 (ColonGPT (w/ LoRA, w/o extra data))
Efficient Multimodal Learning from Data-centric Perspective arXiv:2402.11530