Multi-modal Evaluation on MME
1,846AccuracyVisionZip
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VisionZipBase Model=mini-Gemini 7B, Number of Tokens=1922024.12 | 1,846 | 100.2 | |
| Vanilla 7BBase Model=mini-Gemini 7B, Number of Tokens=576, Protocol=Upper Bound2024.12 | 1,841 | 100 | |
| VisionZipBase Model=mini-Gemini 7B, Number of Tokens=1282024.12 | 1,841 | 100 | |
| VisionZipBase Model=mini-Gemini 7B, Number of Tokens=128, Fine-tuning Protocol=Fine-tuned multimodal projector2024.12 | 1,810 | 98.3 | |
| VisionZipBase Model=mini-Gemini 7B, Number of Tokens=192, Fine-tuning Protocol=Fine-tuned multimodal projector2024.12 | 1,804 | 98 | |
| VisionZipBase Model=mini-Gemini 7B, Number of Tokens=64, Fine-tuning Protocol=Fine-tuned multimodal projector2024.12 | 1,779 | 96.6 | |
| VisionZipBase Model=mini-Gemini 7B, Number of Tokens=642024.12 | 1,737 | 94.4 |