Skywork-VL-Reward-7B
Skywork/Skywork-VL-Reward-7B
Tracked by OpenModelStats since September 26, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 2,854
- Total downloadsCumulative all-time download counter reported by the source platform.
- 47.2K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +448(increase)
- 1.0%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 48
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #1681 among tracked Image Text to Text models.
- #16,274
- 417(up 417 places)this week
- Parameters
- 8.3B
- Last source update
- Jun 10, 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.
- 46.6
- Skywork-VL-Reward-7B gained 448 downloads during the last seven tracked days.
- It moved from #1700 to #1681 among tracked Image Text to Text models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
Skywork-VL-Reward-7B is a image text to text model published by Skywork. OpenModelStats has tracked the model since Sep 26, 2026, most recently observing it Oct 3, 2026.
- Published
- Apr 14, 2025
- Last updated
- Jun 10, 2025
- Library
- transformers
- License
- mit
- Task
- Image Text to Text
- Parameters
- 8,292,166,656
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 64
transformerssafetensorsqwen2_5_vlimage-text-to-textMultimodal Reward ModelReward Modelconversationalarxiv:2505.07263base_model:Qwen/Qwen2.5-VL-7B-Instructbase_model:finetune:Qwen/Qwen2.5-VL-7B-Instructlicense:mittext-generation-inference
Publisher
SkyworkView publisher statistics →Model family
Based on base-model relationships reported by the source's metadata.
Base model
Sibling models
- Qwen2.5-VL-7B-Instruct-AWQ1.8M
- NuMarkdown-8B-Thinking285.3K
- Qwen2.5-VL-7B-Instruct-GGUF179.6K
- olmOCR-2-7B-1025145K
- olmOCR-2-7B-1025-FP8107.4K
- Cosmos-Reason1-7B22.2K
- Rex-Thinker-GRPO-7B3,521
- RolmOCR1,927
Similar models
| Model | DL 30D |
|---|---|
| Qwen2.5-VL-7B-InstructQwen | 5.8M |
| Qwen2.5-VL-7B-Instruct-AWQQwen | 1.8M |
| UI-TARS-1.5-7BByteDance-Seed | 550.8K |
| Qwen2.5-VL-7B-Instruct-abliteratedhuihui-ai | 282.3K |
| olmOCR-2-7B-1025allenai | 145K |
| Cosmos-Reason1-7Bnvidia | 22.2K |