mr9b-qwen35base-v5-scaffold-cispo-h100-215

aviralku/mr9b-qwen35base-v5-scaffold-cispo-h100-215

Reinforcement Learning9.4B parameters
Tracked by OpenModelStats since September 25, 2026View on Hugging Face ↗
Downloads 30D
9
Total downloads
9
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
—
–this week
Parameters
9.4B
Last source update
Sep 25, 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 2026-09-25. Charts appear as daily observations accumulate.

Overview

mr9b-qwen35base-v5-scaffold-cispo-h100-215 is a reinforcement learning model published by aviralku. OpenModelStats has tracked the model since Sep 25, 2026, most recently observing it Sep 27, 2026.

Published
Sep 25, 2026
Last updated
Sep 25, 2026
Library
—
License
—
Task
Reinforcement Learning
Parameters
9,409,813,744
Spaces
—
Derivative models
—
Velocity 7D/day
—
safetensorsqwen3_5reinforcement-learningcispometa-reasoningverlbase_model:Qwen/Qwen3.5-9Bbase_model:finetune:Qwen/Qwen3.5-9Bregion:us

Publisher

aviralkuView publisher statistics →

Derived from Qwen/Qwen3.5-9B (reported by the source; parent not yet tracked).

Similar models

Models similar to mr9b-qwen35base-v5-scaffold-cispo-h100-215
ModelDL 30D
VisualQuality-R1-7BTianheWu3,928
a3-rl-laion_nemotron-gym-agent-calendar-80-8Blaion3,383
a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8Blaion1,688
Open-Reasoner-Zero-7BOpen-Reasoner-Zero1,811
inf-retriever-v1-proinfly2,350
beaver-7b-v1.0-costPKU-Alignment3,199