List your company

Multi-modal Evaluation on MME

1,846AccuracyVisionZip
1,732.641,762.071,791.51,820.93Dec 5, 2024

Evaluation results

MethodLinks
VisionZipBase Model=mini-Gemini 7B, Number of Tokens=1922024.121,846100.2
Vanilla 7BBase Model=mini-Gemini 7B, Number of Tokens=576, Protocol=Upper Bound2024.121,841100
VisionZipBase Model=mini-Gemini 7B, Number of Tokens=1282024.121,841100
VisionZipBase Model=mini-Gemini 7B, Number of Tokens=128, Fine-tuning Protocol=Fine-tuned multimodal projector2024.121,81098.3
VisionZipBase Model=mini-Gemini 7B, Number of Tokens=192, Fine-tuning Protocol=Fine-tuned multimodal projector2024.121,80498
VisionZipBase Model=mini-Gemini 7B, Number of Tokens=64, Fine-tuning Protocol=Fine-tuned multimodal projector2024.121,77996.6
VisionZipBase Model=mini-Gemini 7B, Number of Tokens=642024.121,73794.4