Qwen3-1.7B-GRPO-DeepMath-100-steps

shufanshen/Qwen3-1.7B-GRPO-DeepMath-100-steps

Reinforcement Learning2B parameterstransformersLicense: other

Tracked by OpenModelStats since September 14, 2026View on Hugging Face ↗

Downloads 30D: 0
Total downloads: 0
Gained 7D: 0
Gained 30D: —
Likes: 0; +0 in 7D
Rank · tracked models: —; –this week
Parameters: 2B
Last source update: Sep 14, 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 2026-09-14. Charts appear as daily observations accumulate.

Overview

Qwen3-1.7B-GRPO-DeepMath-100-steps is a reinforcement learning model published by shufanshen. OpenModelStats has tracked the model since Sep 14, 2026, most recently observing it Sep 14, 2026.

Published: Sep 9, 2026
Last updated: Sep 14, 2026
Library: transformers
License: other
Task: Reinforcement Learning
Parameters: 2,031,739,904
Spaces: —
Derivative models: —
Velocity 7D/day: 0

transformerssafetensorsqwen3text-generationgrporeinforcement-learningopdopsftbase_model:Qwen/Qwen3-1.7Bbase_model:finetune:Qwen/Qwen3-1.7Blicense:othertext-generation-inference

Publisher

shufanshenView publisher statistics →

Derived from Qwen/Qwen3-1.7B (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-1.7B-GRPO-DeepMath-100-steps
Model	Task	DL 30D	Likes	Params
OphVLM-R1QiZishi	Reinforcement Learning	1,546	1	2.3B
Qwen3-4B-Instruct-2507.prestar-RL.reason-only.lr7e-7-kl0.step-2176JackHsieh	Reinforcement Learning	334	0	4B
OpenThinker3-7B-SFT-GRPO-DEDGurgurov	Reinforcement Learning	6,730	0	952M
beaver-7b-v1.0-costPKU-Alignment	Reinforcement Learning	3,930	10	6.6B
beaver-7b-v1.0-rewardPKU-Alignment	Reinforcement Learning	3,163	17	6.6B
inf-retriever-v1-proinfly	Reinforcement Learning	2,350	7	7.1B