VideoScore2
TIGER-Lab/VideoScore2
Tracked by OpenModelStats since September 3, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 4,135
- Total downloadsCumulative all-time download counter reported by the source platform.
- 68.1K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +1,633(increase)
- 2.5%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 5
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #8 among tracked Visual Question Answering models.
- #13,078
- 36(down 36 places)this week
- Parameters
- 8.3B
- Last source update
- Oct 14, 2025
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 59.9
- VideoScore2 gained 1,633 downloads during the last seven tracked days.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
VideoScore2 is a visual question answering model published by TIGER-Lab. OpenModelStats has tracked the model since Sep 3, 2026, most recently observing it Oct 3, 2026.
- Published
- Sep 19, 2025
- Last updated
- Oct 14, 2025
- Library
- —
- License
- apache-2.0
- Task
- Visual Question Answering
- Parameters
- 8,292,166,656
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 233
safetensorsqwen2_5_vlvisual-question-answeringendataset:TIGER-Lab/VideoFeedback2arxiv:2509.22799base_model:Qwen/Qwen2.5-VL-7B-Instructbase_model:finetune:Qwen/Qwen2.5-VL-7B-Instructlicense:apache-2.0region:us
Publisher
TIGER-LabView publisher statistics →Derived from Qwen/Qwen2.5-VL-7B-Instruct (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| VideoScoreTIGER-Lab | 52 |
| VideoLLaMA2.1-7B-AVDAMO-NLP-SG | 2,360 |
| MiniCPM-Llama3-V-2_5-int4openbmb | 249 |
| llava-med-v1.5-mistral-7b-hfchaoyinshe | 1,886 |
| MechVL-4B-RLXiaofengAlg | 756 |
| Ivy-VL-llavaAI-Safeguard | 179 |