Multimodal Understanding on MMBench (MMB) en (test)
67.6ScoreDense Connector
Evaluation Results
| Method | Links | |
|---|---|---|
| Dense ConnectorResolution=336, Tokens=144, PT+IT=0.5M+0.6M, LLM=Vicuna-7B2024.05 | 67.6 | |
| TokenPackerResolution=336, Tokens=144, PT+IT=0.5M+0.6M, LLM=Vicuna-7B2024.05 | 65.1 | |
| LLaVAResolution=336, Tokens=576, PT+IT=0.5M+0.6M, LLM=Vicuna-7B2024.05 | 64.3 |