📊 Showing 5 results | 📏 Metric: GPT-3.5 score
| Rank | Model | Paper | GPT-3.5 score | Date | Code |
|---|---|---|---|---|---|
| 1 | LLaVA-InternLM2-ViT + MoSLoRA | Mixture-of-Subspaces in Low-Rank Adaptation | 73.80 | 2024-06-16 | 📦 wutaiqiang/moslora |
| 2 | CuMo-7B | CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts | 73.00 | 2024-05-09 | 📦 shi-labs/cumo |
| 3 | LLaVA-LLaMA3-8B-ViT + MoSLoRA | Mixture-of-Subspaces in Low-Rank Adaptation | 73.00 | 2024-06-16 | 📦 wutaiqiang/moslora |
| 4 | Video-LaVIT | Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization | 67.30 | 2024-02-05 | 📦 jy0205/lavit |
| 5 | DreamLLM-7B | DreamLLM: Synergistic Multimodal Comprehension and Creation | 49.90 | 2023-09-20 | 📦 RunpeiDong/DreamLLM |