Zhang199
Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-16-512
No description available.
Model Documentation
Here, we introduce TinyLLaVA-Video-Qwen2.5-3B-Group-16-512. For LLM and vision tower, we choose Qwen2.5-3B and siglip-so400m-patch14-384, respectively. The model adopts the Video-Level Group Resampler, samples 16 frames from each video, and represents the video sequence using 512 tokens.
Result
| Model (HF Path) | #Frame/Query | Video-MME | MVBench | LongVideoBench | MLVU | | :----------------------------------------: | :------------: | :-------------: | :-------: | :--------------: | :----------: | | Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-1fps-512 | 1fps/512 | 47.7 | 47.0 | 42.0 | 52.6 | | Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-16-512 | 16/512 | 47.0 | 45.5 | 42.4 | 52.5 | | Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Naive-16-512 | 16/512 | 44.7 | 42.5 | 37.6 | 48.1 | | Zhang199/TinyLLaVA-Video-Phi2-Naive-16-512 | 16/512 | 42.7 | 42.0 | 42.2 | 46.5 |Files & Weights
| Filename | Size | Action |
|---|---|---|
| model-00001-of-00002.safetensors | 4.62 GB | |
| model-00002-of-00002.safetensors | 2.14 GB | |
| training_args.bin | 0.00 GB |