MATH-Llama-3.2-3B-SimKO-TS2-nosquare

xzybit/MATH-Llama-3.2-3B-SimKO-TS2-nosquare

Reinforcement Learning3.6B parametersLicense: llama3.2

Tracked by OpenModelStats since September 21, 2026View on Hugging Face ↗

Downloads 30D: 7
Total downloads: 35
Gained 7D: —
Gained 30D: —
Likes: 1
Rank · tracked models: —; –this week
Parameters: 3.6B
Last source update: May 15, 2026

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-21. Charts appear as daily observations accumulate.

Overview

MATH-Llama-3.2-3B-SimKO-TS2-nosquare is a reinforcement learning model published by xzybit. OpenModelStats has tracked the model since Sep 21, 2026, most recently observing it Sep 28, 2026.

Published: May 15, 2026
Last updated: May 15, 2026
Library: —
License: llama3.2
Task: Reinforcement Learning
Parameters: 3,606,752,256
Spaces: —
Derivative models: —
Velocity 7D/day: —

safetensorsllamamathreasoningsimkoreinforcement-learningpass@kbase_model:meta-llama/Llama-3.2-3B-Instructbase_model:finetune:meta-llama/Llama-3.2-3B-Instructlicense:llama3.2region:us

Publisher

xzybitView publisher statistics →

Derived from meta-llama/Llama-3.2-3B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to MATH-Llama-3.2-3B-SimKO-TS2-nosquare
Model	Task	DL 30D	Likes	Params
Qwen3-4B-Instruct-2507.prestar-RL.reason-only.lr7e-7-kl0.step-2176JackHsieh	Reinforcement Learning	334	0	4B
VFIG-4BXunmeiLiu	Reinforcement Learning	300	8	4.4B
OphVLM-R1QiZishi	Reinforcement Learning	3,003	1	2.3B
beaver-7b-v1.0-costPKU-Alignment	Reinforcement Learning	2,842	10	6.6B
beaver-7b-v1.0-rewardPKU-Alignment	Reinforcement Learning	2,124	17	6.6B
inf-retriever-v1-proinfly	Reinforcement Learning	2,350	7	7.1B