qwen38-27b-math-grpo-baseline-drgrpo-step100

andresnowak/qwen38-27b-math-grpo-baseline-drgrpo-step100

Reinforcement Learning27.4B parameterstransformersLicense: apache-2.0

Tracked by OpenModelStats since September 23, 2026View on Hugging Face ↗

Downloads 30D: 19
Total downloads: 19
Gained 7D: —
Gained 30D: —
Likes: 0
Rank · tracked models: —; –this week
Parameters: 27.4B
Last source update: Sep 23, 2026

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-23. Charts appear as daily observations accumulate.

Overview

qwen38-27b-math-grpo-baseline-drgrpo-step100 is a reinforcement learning model published by andresnowak. OpenModelStats has tracked the model since Sep 23, 2026, most recently observing it Sep 24, 2026.

Published: Sep 23, 2026
Last updated: Sep 23, 2026
Library: transformers
License: apache-2.0
Task: Reinforcement Learning
Parameters: 27,356,728,560
Spaces: —
Derivative models: —
Velocity 7D/day: —

transformerssafetensorsqwen3_5image-text-to-textreinforcement-learninggrpodr-grpochain-of-thoughtresearch-checkpointbase_model:Qwen/Qwen3.8-27Bbase_model:finetune:Qwen/Qwen3.8-27Blicense:apache-2.0

Publisher

andresnowakView publisher statistics →

Derived from Qwen/Qwen3.8-27B (reported by the source; parent not yet tracked).

Similar models

Models similar to qwen38-27b-math-grpo-baseline-drgrpo-step100
Model	Task	DL 30D	Params
jtd-d5-69-30Blaion	Reinforcement Learning	42	30.5B
jtd-d0-69-30Blaion	Reinforcement Learning	38	30.5B
jtd-d3-60-30Blaion	Reinforcement Learning	38	30.5B
jtd-d2-20-30Blaion	Reinforcement Learning	35	30.5B
jtd-d4-34-30Blaion	Reinforcement Learning	34	30.5B
jtd-d1-18-30Blaion	Reinforcement Learning	33	30.5B