The collection for the Paper "Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning"
🔄 In a Training Loop
Mingyang Song
Nickyang
AI & ML interests
LRMs, Long-Context LLMs, LLM Judges, Many-Shot ICL
Organizations
None yet
models 5
Nickyang/ConciseR-Zero-7B-Preview
Text Generation • 8B • Updated • 5 • 2
Nickyang/ConciseR-Zero-7B
Text Generation • 8B • Updated • 7 • 1
Nickyang/FastCuRL-1.5B-V3
Text Generation • 2B • Updated • 14 • • 4
Nickyang/FastCuRL-1.5B-V2
Text Generation • 2B • Updated • 8 • 1
Nickyang/FastCuRL-1.5B-Preview
Text Generation • 2B • Updated • 3 • 8