metadata
license: apache-2.0
pipeline_tag: image-text-to-text
Here, we introduce TinyLLaVA-Video-Phi2-16-512. For LLM and vision tower, we choose Phi-2 and siglip-so400m-patch14-384, respectively. The model samples 16 frames from each video and represents the video sequence using 512 tokens.
Result
| VT (HF Path) | #Frame/Query | Video-MME | MVBench | LongVideoBench | MLVU |
|---|---|---|---|---|---|
| Zhang199/TinyLLaVA-Video-Qwen2.5-3B-16-512 | 16/512 | 44.7 | 42.5 | 37.6 | 48.1 |
| Zhang199/TinyLLaVA-Video-Phi2-16-512 | 16/512 | 42.7 | 42.0 | 42.2 | 46.5 |