Qwen3-4B-Instruct-2507.prestar-RL.reason-only.lr7e-7-kl0.step-2176

JackHsieh/Qwen3-4B-Instruct-2507.prestar-RL.reason-only.lr7e-7-kl0.step-2176

Reinforcement Learning4B parametersLicense: apache-2.0

Tracked by OpenModelStats since September 19, 2026View on Hugging Face ↗

Downloads 30D: 334
Total downloads: 334
Gained 7D: —
Gained 30D: —
Likes: 0
Rank · tracked models: #48,370; 341(down 341 places)this week
Parameters: 4B
Last source update: Sep 26, 2026

It moved from #115 to #114 among tracked Reinforcement Learning models this week.

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

Overview

Qwen3-4B-Instruct-2507.prestar-RL.reason-only.lr7e-7-kl0.step-2176 is a reinforcement learning model published by JackHsieh. OpenModelStats has tracked the model since Sep 19, 2026, most recently observing it Sep 27, 2026.

Published: Sep 19, 2026
Last updated: Sep 26, 2026
Library: —
License: apache-2.0
Task: Reinforcement Learning
Parameters: 4,022,468,096
Spaces: —
Derivative models: —
Velocity 7D/day: —

safetensorsqwen3prestarreinforcement-learningrlooverlbase_model:Qwen/Qwen3-4B-Instruct-2507base_model:finetune:Qwen/Qwen3-4B-Instruct-2507license:apache-2.0region:us

Publisher

JackHsiehView publisher statistics →

Derived from Qwen/Qwen3-4B-Instruct-2507 (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-4B-Instruct-2507.prestar-RL.reason-only.lr7e-7-kl0.step-2176
Model	Task	DL 30D	Likes	Params
VFIG-4BXunmeiLiu	Reinforcement Learning	300	8	4.4B
beaver-7b-v1.0-costPKU-Alignment	Reinforcement Learning	3,295	10	6.6B
beaver-7b-v1.0-rewardPKU-Alignment	Reinforcement Learning	2,722	17	6.6B
OphVLM-R1QiZishi	Reinforcement Learning	2,976	1	2.3B
inf-retriever-v1-proinfly	Reinforcement Learning	2,350	7	7.1B
Open-Reasoner-Zero-7BOpen-Reasoner-Zero	Reinforcement Learning	1,811	34	7.6B