L1 L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning l3lab/L1-Qwen-7B-Max 8B • Updated Jul 13, 2025 • 51 l3lab/L1-Qwen3-8B-Max 8B • Updated Jul 13, 2025 • 62 l3lab/L1-Qwen-7B-Exact 8B • Updated Jul 13, 2025 • 130 • 1 l3lab/L1-Qwen3-8B-Exact 8B • Updated Jul 13, 2025 • 41 • 1
miniCTX miniCTX: Neural Theorem Proving with (Long-)Contexts (ICLR 2025 Oral) l3lab/ntp-mathlib-context-deepseek-coder-1.3b Text Generation • Updated Sep 6, 2024 • 200 • 3 l3lab/ntp-mathlib-instruct-context Viewer • Updated Sep 6, 2024 • 614k • 198 • 2 l3lab/ntp-mathlib-st-deepseek-coder-1.3b Text Generation • Updated Sep 6, 2024 • 84 l3lab/ntp-mathlib Viewer • Updated Sep 6, 2024 • 213k • 191 • 2
L1 L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning l3lab/L1-Qwen-7B-Max 8B • Updated Jul 13, 2025 • 51 l3lab/L1-Qwen3-8B-Max 8B • Updated Jul 13, 2025 • 62 l3lab/L1-Qwen-7B-Exact 8B • Updated Jul 13, 2025 • 130 • 1 l3lab/L1-Qwen3-8B-Exact 8B • Updated Jul 13, 2025 • 41 • 1
miniCTX miniCTX: Neural Theorem Proving with (Long-)Contexts (ICLR 2025 Oral) l3lab/ntp-mathlib-context-deepseek-coder-1.3b Text Generation • Updated Sep 6, 2024 • 200 • 3 l3lab/ntp-mathlib-instruct-context Viewer • Updated Sep 6, 2024 • 614k • 198 • 2 l3lab/ntp-mathlib-st-deepseek-coder-1.3b Text Generation • Updated Sep 6, 2024 • 84 l3lab/ntp-mathlib Viewer • Updated Sep 6, 2024 • 213k • 191 • 2
