math-adapter-grpo-l45-g4b-grpo_lr1e-5_s42_rv2_mn2048_mt1

Yuivdldk/math-adapter-grpo-l45-g4b-grpo_lr1e-5_s42_rv2_mn2048_mt1

Reinforcement LearningpeftLicense: gemma
Tracked by OpenModelStats since September 12, 2026View on Hugging Face ↗
Downloads 30D
9
Total downloads
9
Gained 7D
0
Gained 30D
—
Likes
0
+0 in 7D
Rank · tracked models
—
–this week
Parameters
—
Last source update
Sep 10, 2026

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 2026-09-12. Charts appear as daily observations accumulate.

Overview

math-adapter-grpo-l45-g4b-grpo_lr1e-5_s42_rv2_mn2048_mt1 is a reinforcement learning model published by Yuivdldk. OpenModelStats has tracked the model since Sep 12, 2026, most recently observing it Sep 11, 2026.

Published
Aug 3, 2026
Last updated
Sep 10, 2026
Library
peft
License
gemma
Task
Reinforcement Learning
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
0
peftsafetensorsgemmagrporeinforcement-learningmathbase_model:google/gemma-3-4b-itbase_model:adapter:google/gemma-3-4b-itlicense:gemmaregion:us

Publisher

YuivdldkView publisher statistics →

Derived from google/gemma-3-4b-it (reported by the source; parent not yet tracked).

Similar models

Models similar to math-adapter-grpo-l45-g4b-grpo_lr1e-5_s42_rv2_mn2048_mt1
ModelDL 30D
ppo-seals-CartPole-v0HumanCompatibleAI170K
ppo-Pendulum-v1HumanCompatibleAI40.6K
NoveltyAdapt-policieshelenlu9423.9K
Tifa-Deepsex-14b-CoT-GGUFmradermacher21.3K
sac-BipedalWalkerHardcore-v3sb38,773
Qwen3-14B-ARPO-DeepSearch-i1-GGUFmradermacher7,560