klear-agentforge-8b-critic-v9-epoch2-5

sisizhang/klear-agentforge-8b-critic-v9-epoch2-5

Reinforcement Learning7.6B parametersLicense: mit
Tracked by OpenModelStats since November 8, 2026View on Hugging Face ↗
Downloads 30D
27
Total downloads
27
Gained 7D
—
Gained 30D
—
Likes
0
Rank · tracked models
—
–this week
Parameters
7.6B
Last source update
Nov 10, 2026

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-11-08. Charts appear as daily observations accumulate.

Overview

klear-agentforge-8b-critic-v9-epoch2-5 is a reinforcement learning model published by sisizhang. OpenModelStats has tracked the model since Nov 8, 2026, most recently observing it Nov 11, 2026.

Published
Nov 8, 2026
Last updated
Nov 10, 2026
Library
—
License
mit
Task
Reinforcement Learning
Parameters
7,568,409,601
Spaces
—
Derivative models
—
Velocity 7D/day
—
safetensorsqwen3code-agentreinforcement-learningcriticvalue-modelprocess-rewardenzhdataset:sisizhang/swesmith-critic-ppo-tasksbase_model:Kwai-Klear/Klear-AgentForge-8B-SFTbase_model:finetune:Kwai-Klear/Klear-AgentForge-8B-SFT

Publisher

sisizhangView publisher statistics →

Derived from Kwai-Klear/Klear-AgentForge-8B-SFT (reported by the source; parent not yet tracked).

Similar models

Models similar to klear-agentforge-8b-critic-v9-epoch2-5
ModelDL 30D
Open-Reasoner-Zero-7BOpen-Reasoner-Zero3,091
inf-retriever-v1-proinfly2,350
a3-rl-laion_nemotron-gym-agent-calendar-80-8Blaion3,383
a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8Blaion1,688
VisualQuality-R1-7BTianheWu1,158
beaver-7b-v1.0-costPKU-Alignment2,050