Qwen3-14B-ARPO-DeepSearch-i1-GGUF

mradermacher/Qwen3-14B-ARPO-DeepSearch-i1-GGUF

Reinforcement LearningtransformersLicense: mit
Tracked by OpenModelStats since October 1, 2026View on Hugging Face ↗
Downloads 30D
7,028
Total downloads
15.2K
Gained 7D
—
Gained 30D
—
Likes
1
Rank · tracked models
#19,420
60(up 60 places)this week
Parameters
—
Last source update
Dec 25, 2025
  • It moved from #34 to #35 among tracked Reinforcement Learning models this week.

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen3-14B-ARPO-DeepSearch-i1-GGUF is a reinforcement learning model published by mradermacher. OpenModelStats has tracked the model since Oct 1, 2026, most recently observing it 4h ago.

Published
Jul 31, 2025
Last updated
Dec 25, 2025
Library
transformers
License
mit
Task
Reinforcement Learning
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformersggufagenttool-usereinforcement-learningqwenllmenbase_model:dongguanting/Qwen3-14B-ARPO-DeepSearchbase_model:quantized:dongguanting/Qwen3-14B-ARPO-DeepSearchlicense:mitendpoints_compatible

Publisher

mradermacherView publisher statistics →

Derived from dongguanting/Qwen3-14B-ARPO-DeepSearch (reported by the source; parent not yet tracked).

Similar models

Models similar to Qwen3-14B-ARPO-DeepSearch-i1-GGUF
ModelDL 30D
ppo-seals-CartPole-v0HumanCompatibleAI171.7K
ppo-Pendulum-v1HumanCompatibleAI46.1K
Tifa-Deepsex-14b-CoT-GGUFmradermacher20.9K
NoveltyAdapt-policieshelenlu9420.7K
sac-BipedalWalkerHardcore-v3sb38,772
decision-transformer-gym-hopper-mediumedbeeching6,467