Rex-Thinker-GRPO-7B
IDEA-Research/Rex-Thinker-GRPO-7B
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 3,533
- Total downloadsCumulative all-time download counter reported by the source platform.
- 8,692
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +13(increase)
- 0.3%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 11
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #17 among tracked Zero Shot Object Detection models.
- #14,433
- 49(down 49 places)this week
- Parameters
- 8.3B
- Last source update
- Jun 9, 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.
- 22.1
- Rex-Thinker-GRPO-7B gained 13 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
Rex-Thinker-GRPO-7B is a zero shot object detection model published by IDEA-Research. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 6, 2026.
- Published
- May 23, 2025
- Last updated
- Jun 9, 2025
- Library
- transformers
- License
- —
- Task
- Zero Shot Object Detection
- Parameters
- 8,292,166,656
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 2
transformerssafetensorsqwen2_5_vlimage-text-to-textzero-shot-object-detectionenarxiv:2506.04034base_model:Qwen/Qwen2.5-VL-7B-Instructbase_model:finetune:Qwen/Qwen2.5-VL-7B-Instructtext-generation-inferenceendpoints_compatibleregion:us
Model family
Based on base-model relationships reported by the source's metadata.
Base model
Sibling models
- Qwen2.5-VL-7B-Instruct-AWQ1.7M
- NuMarkdown-8B-Thinking234K
- Qwen2.5-VL-7B-Instruct-GGUF190.1K
- olmOCR-2-7B-1025124.8K
- olmOCR-2-7B-1025-FP8103.8K
- Cosmos-Reason1-7B21.3K
- Skywork-VL-Reward-7B3,079
- RolmOCR1,830
Similar models
| Model | DL 30D |
|---|---|
| owlv2-large-patch14-ensemblegoogle | 112.6K |
| mm_grounding_dino_large_allopenmmlab-community | 55.2K |
| llmdet_largeiSEE-Laboratory | 4,612 |
| mm_grounding_dino_large_o365v2_oiv6_goldgopenmmlab-community | 1,209 |
| llmdet_baseiSEE-Laboratory | 105.3K |
| mm_grounding_dino_base_allopenmmlab-community | 2,841 |