Qwen2.5-3B-GRPO-Staleness-4

zbeeb/Qwen2.5-3B-GRPO-Staleness-4

Text Generation3.1B parameterstransformersLicense: other
Tracked by OpenModelStats since September 18, 2026View on Hugging Face ↗
Downloads 30D
309
Total downloads
309
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
#50,258
467(down 467 places)this week
Parameters
3.1B
Last source update
Sep 18, 2026
Momentum
0.0
  • It moved from #15420 to #15595 among tracked Text Generation models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen2.5-3B-GRPO-Staleness-4 is a text generation model published by zbeeb. OpenModelStats has tracked the model since Sep 18, 2026, most recently observing it Sep 20, 2026.

Published
Sep 18, 2026
Last updated
Sep 18, 2026
Library
transformers
License
other
Task
Text Generation
Parameters
3,085,938,688
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsqwen2text-generationgrpomathreinforcement-learningstaleness-grpoconversationalenzhdataset:zbeeb/Staleness-GRPO-DAPO-Math-17k

Publisher

zbeebView publisher statistics →

Derived from Qwen/Qwen2.5-3B (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen2.5-3B-GRPO-Staleness-4
ModelDL 30D
Qwen2.5-3B-InstructQwen4.3M
Qwen2.5-Coder-3B-InstructQwen522.9K
Qwen2.5-3BQwen277.5K
Qwen2.5-Coder-3BQwen36.5K
Qwen2.5-3B-Instructunsloth21.7K
Qwen2.5-3B-Instruct-4bitmlx-community13.6K
zbeeb/Qwen2.5-3B-GRPO-Staleness-4 — Downloads, Growth & Stats | OpenModelStats