Downloads · 30 days
15
3% of all-time downloads
TinyLLaVA-Video-Qwen2.5-3B-Group-1fps-512
Zhang199/TinyLLaVA-Video-Qwen2.5-3B-Group-1fps-512
TinyLLaVA-Video-Qwen2.5-3B-Group-1fps-512 is a video-text-to-text model from Zhang199. Use it for the video-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
<center<span style="font-size:2em;"TinyLLaVA-Video</span</center
All-time downloads
586
Public
Parameters
3.6B
7.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.3 GB · 100%
At a glance
- Task
- Video-Text-to-Text
- License
- apache-2.0
- Model type
- tinyllava
- Access
- Public
- Created
- Mar 19, 2025
- Updated
- Apr 24, 2025
- SHA
- dd06f5da
Model card
From the Hugging Face model README
<center><span style="font-size:2em;">TinyLLaVA-Video</span></center>
Here, we introduce TinyLLaVA-Video-Qwen2.5-3B-Group-1fps-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 one frame per second (1fps) based on the length of 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-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 |
- Task
- Video-Text-to-Text
- Type
- tinyllava
- License
- apache-2.0
- Created
- Mar 19, 2025
- Updated
- Apr 24, 2025