REG on ColonINST (seen)
99.96AccuracyColonGPT
Evaluation Results
| Method | Links | |
|---|---|---|
| ColonGPTVisual encoder=SigLIP-SO (384px), Language model=Phi1.5 (1.3B), LoRA=false, EXT=false2024.10 | 99.96 | |
| LLaVA-v1.5Visual encoder=CLIP-L/14 (336px), Language model=Vicuna-v1.5 (7B), LoRA=true, EXT=true2024.10 | 99.32 | |
| LLaVA-Med-v1.5Visual encoder=CLIP-L/14 (224px), Language model=Mistral-v0.2 (7B), LoRA=true, EXT=false2024.10 | 99.3 | |
| MGM-2BVisual encoder=CLIP-L/14 (336px) & ConvNeXt-L (768px), Language model=Gemma (2B), LoRA=true, EXT=false2024.10 | 98.75 | |
| LLaVA-v1.5Visual encoder=CLIP-L/14 (336px), Language model=Vicuna-v1.5 (7B), LoRA=true, EXT=false2024.10 | 98.58 | |
| MGM-2BVisual encoder=CLIP-L/14 (336px) & ConvNeXt-L (768px), Language model=Gemma (2B), LoRA=false, EXT=false2024.10 | 98.17 | |
| MobileVLM-1.7BVisual encoder=CLIP-L/14 (336px), Language model=MobileLLaMA (1.4B), LoRA=true, EXT=true2024.10 | 97.87 | |
| MobileVLM-1.7BVisual encoder=CLIP-L/14 (336px), Language model=MobileLLaMA (1.4B), LoRA=true, EXT=false2024.10 | 97.78 | |
| LLaVA-Med-v1.0Visual encoder=CLIP-L/14 (224px), Language model=LLaMA1 (7B), LoRA=false, EXT=false2024.10 | 97.74 | |
| LLaVA-Med-v1.0Visual encoder=CLIP-L/14 (224px), Language model=LLaMA1 (7B), LoRA=true, EXT=false2024.10 | 97.35 | |
| Bunny-v1.0-3BVisual encoder=SigLIP-SO (384px), Language model=Phi2 (2.7B), LoRA=true, EXT=false2024.10 | 96.61 | |
| Bunny-v1.0-3BVisual encoder=SigLIP-SO (384px), Language model=Phi2 (2.7B), LoRA=true, EXT=true2024.10 | 96.02 | |
| MiniGPT-v2Visual encoder=EVA-G/14 (448px), Language model=LLaMA2 (7B), LoRA=false, EXT=false2024.10 | 94.69 | |
| LLaVA-Med-v1.5Visual encoder=CLIP-L/14 (224px), Language model=Mistral-v0.2 (7B), LoRA=false, EXT=false2024.10 | 90.4 | |
| MiniGPT-v2Visual encoder=EVA-G/14 (448px), Language model=LLaMA2 (7B), LoRA=true, EXT=true2024.10 | 87.65 | |
| LLaVA-v1Visual encoder=CLIP-L/14 (224px), Language model=Vicuna-v1.3 (7B), LoRA=true, EXT=true2024.10 | 86.87 | |
| LLaVA-v1Visual encoder=CLIP-L/14 (224px), Language model=Vicuna-v1.3 (7B), LoRA=true, EXT=false2024.10 | 84.55 |