ThinkPrune - a Shiyu-Lab Collection

Shiyu-Lab 's Collections

Prereq-Tune_Models

ThinkPrune

updated Apr 23

ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-iter2k

Text Generation • 2B • Updated Apr 8 • 1.01k • 1
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-2k

Text Generation • 2B • Updated Apr 8 • 7
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-4k

Text Generation • 2B • Updated Apr 8 • 513
Shiyu-Lab/QwQ-32B-thinkprune-4k

Text Generation • 33B • Updated Apr 8 • 2
Shiyu-Lab/QwQ-32B-thinkprune-3k

Text Generation • 33B • Updated Apr 8 • 3
Shiyu-Lab/QwQ-32B-thinkprune-2k

Text Generation • 33B • Updated Apr 8 • 2
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-iter3k

Text Generation • 2B • Updated Apr 8 • 6
Shiyu-Lab/DeepScaleR-1.5B-Preview-thinkprune-4k

Text Generation • 2B • Updated Apr 8 • 7
Shiyu-Lab/DeepScaleR-1.5B-Preview-thinkprune-3k

Text Generation • 2B • Updated Apr 8 • 11
Shiyu-Lab/DeepScaleR-1.5B-Preview-thinkprune-2k

Text Generation • 2B • Updated Apr 8 • 9
Shiyu-Lab/DeepScaleR-1.5B-Preview-thinkprune-iter2k

Text Generation • 2B • Updated Apr 8 • 1k
Shiyu-Lab/DeepScaleR-1.5B-Preview-thinkprune-iter3k

Text Generation • 2B • Updated Apr 8 • 11
Shiyu-Lab/QwQ-32B-thinkprune-iter3k

Text Generation • 33B • Updated Apr 8 • 4
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-3k

Text Generation • 2B • Updated Apr 8 • 9
Shiyu-Lab/QwQ-32B-thinkprune-iter2k

Text Generation • 33B • Updated Apr 23 • 2