MiniCPM5-2B-SWE-smith-GRPO

zzzluvst/MiniCPM5-2B-SWE-smith-GRPO

Reinforcement LearningLicense: apache-2.0
Tracked by OpenModelStats since September 20, 2026View on Hugging Face ↗
Downloads 30D
0
Total downloads
0
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
—
–this week
Parameters
—
Last source update
Sep 21, 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 2026-09-20. Charts appear as daily observations accumulate.

Overview

MiniCPM5-2B-SWE-smith-GRPO is a reinforcement learning model published by zzzluvst. OpenModelStats has tracked the model since Sep 20, 2026, most recently observing it Sep 21, 2026.

Published
Sep 20, 2026
Last updated
Sep 21, 2026
Library
—
License
apache-2.0
Task
Reinforcement Learning
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
—
safetensorsreinforcement-learninggrposwe-agentswe-smithagent-lightningverlminicpmenbase_model:openbmb/MiniCPM5-2Bbase_model:finetune:openbmb/MiniCPM5-2Blicense:apache-2.0

Publisher

zzzluvstView publisher statistics →

Derived from openbmb/MiniCPM5-2B (reported by the source; parent not yet tracked).

Similar models

Models similar to MiniCPM5-2B-SWE-smith-GRPO
ModelDL 30D
ppo-seals-CartPole-v0HumanCompatibleAI138.9K
ppo-Pendulum-v1HumanCompatibleAI39.6K
NoveltyAdapt-policieshelenlu9420.7K
Tifa-Deepsex-14b-CoT-GGUFmradermacher18.5K
VisualQuality-R1-7BTianheWu7,396
decision-transformer-gym-hopper-mediumedbeeching6,592
zzzluvst/MiniCPM5-2B-SWE-smith-GRPO — Downloads, Growth & Stats | OpenModelStats