SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo

PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo

3.4B parameters
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
283
Total downloads
4,564
Gained 7D
+56(increase)
1.3%(up) vs baseline
Gained 30D
—
Likes
1
+0 in 7D
Rank · tracked models
#41,155
1638(down 1638 places)this week
Parameters
3.4B
Last source update
Mar 12, 2025
Momentum
26.8
  • SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo gained 56 downloads during the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo is an AI model published by PeterJinGo. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Sep 29, 2026.

Published
Mar 12, 2025
Last updated
Mar 12, 2025
Library
—
License
—
Task
—
Parameters
3,397,103,616
Spaces
0
Derivative models
—
Velocity 7D/day
8
safetensorsqwen2region:us

Similar models

Models similar to SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo
ModelDL 30D
Qwen2.5-3B-Instruct-AWQQwen524.8K
Qwen2.5-Coder-3B-Instruct-AWQQwen14K
CompassVerifier-3Bopencompass1,175
DeltaP2S-Qwen2.5-3B-P2S-QwenCoder1.5B-Code-S13g-assismoraes618
Arcee-VyLinharcee-ai587
ToolRL-Qwen2.5-3Bchengq9583
PeterJinGo/SearchR1-nq_hotpotqa_train-qwen2.5-3b-em-ppo — Downloads, Growth & Stats | OpenModelStats