TimeChat-Captioner-GRPO-7B
yaolily/TimeChat-Captioner-GRPO-7B
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 967
- Total downloadsCumulative all-time download counter reported by the source platform.
- 8,723
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +137(increase)
- 1.8%(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. #37 among tracked Video Text To Text models.
- #42,125
- 6741(up 6741 places)this week
- Parameters
- 8.9B
- Last source update
- Feb 11, 2026
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 38.9
- TimeChat-Captioner-GRPO-7B gained 137 downloads during the last seven tracked days.
- It moved from #44 to #37 among tracked Video Text To Text models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
TimeChat-Captioner-GRPO-7B is a video text to text model published by yaolily. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 5, 2026.
- Published
- Feb 9, 2026
- Last updated
- Feb 11, 2026
- Library
- transformers
- License
- —
- Task
- Video Text To Text
- Parameters
- 8,931,813,888
- Spaces
- 1
- Derivative models
- —
- Velocity 7D/day
- 20
transformerssafetensorsqwen2_5_omnitext-to-audiovideo-text-to-textarxiv:2602.08711base_model:Qwen/Qwen2.5-Omni-7Bbase_model:finetune:Qwen/Qwen2.5-Omni-7Bendpoints_compatibleregion:us
Publisher
yaolilyView publisher statistics →Model family
Based on base-model relationships reported by the source's metadata.
Base model
- Qwen2.5-Omni-7B320.3K
Sibling models
Similar models
| Model | DL 30D |
|---|---|
| RankVideohltcoe | 12.7K |
| TimeLens2-8BMCG-NJU | 1,303 |
| TimeLens-8BTencentARC | 1,254 |
| JoyAI-VL-Interactionjdopensource | 591 |
| JoyAI-VL-Interaction-Previewjdopensource | 337 |
| JoyAI-VL-Interaction-INT4jdopensource | 296 |