Safety Alignment on MM-SafetyBench
91.61SafetySaFeR-ToolKit (+ SFT+DPO+GRPO) [7B]
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SaFeR-ToolKit (+ SFT+DPO+GRPO) [7B]Model Scale=7B, Training Configuration=SFT+DPO+GRPO2026.03 | 91.61 | 76.01 | 95.65 | |
| SaFeR-ToolKit (+ SFT+DPO+GRPO) [3B]Model Scale=3B, Training Configuration=SFT+DPO+GRPO2026.03 | 90.42 | 70.83 | 94.29 | |
| Qwen2.5-VL-7BModel Scale=7B2026.03 | 48.04 | 47.74 | 16.9 | |
| Qwen2.5-VL-3BModel Scale=3B2026.03 | 20.42 | 51.79 | 4.17 |