grpo-qwen25-3b-math345

logan7000/grpo-qwen25-3b-math345

Reinforcement Learning241.7K parametersLicense: apache-2.0
Tracked by OpenModelStats since September 30, 2026View on Hugging Face ↗
Downloads 30D
59
Total downloads
239
Gained 7D
0
Gained 30D
—
Likes
0
+0 in 7D
Rank · tracked models
—
–this week
Parameters
241.7K
Last source update
Aug 31, 2026

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-30. Charts appear as daily observations accumulate.

Overview

grpo-qwen25-3b-math345 is a reinforcement learning model published by logan7000. OpenModelStats has tracked the model since Sep 30, 2026, most recently observing it Sep 1, 2026.

Published
May 29, 2026
Last updated
Aug 31, 2026
Library
—
License
apache-2.0
Task
Reinforcement Learning
Parameters
241,664
Spaces
—
Derivative models
—
Velocity 7D/day
0
safetensorsqwen2grpomathreasoningreinforcement-learningenbase_model:Qwen/Qwen2.5-3Bbase_model:finetune:Qwen/Qwen2.5-3Blicense:apache-2.0region:us

Publisher

logan7000View publisher statistics →

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

Similar models

Models similar to grpo-qwen25-3b-math345
ModelDL 30D
MusaCoder-27BMooreThreads62
jatjat-project183
OpenThinker3-7B-SFT-GRPO-DEDGurgurov4,210
OphVLM-R1QiZishi2,984
Qwen3-4B-Instruct-2507.prestar-RL.reason-only.lr7e-7-kl0.step-2176JackHsieh334
VFIG-4BXunmeiLiu300
logan7000/grpo-qwen25-3b-math345 — Downloads, Growth & Stats | OpenModelStats