L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
L3 Lab
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 11
l3lab/L1-Qwen3-8B-Max
8B • Updated
• 82
l3lab/L1-Qwen3-8B-Exact
8B • Updated
• 1.02k • 1
l3lab/L1-Qwen-7B-Max
8B • Updated
• 42
l3lab/L1-Qwen-7B-Exact
8B • Updated
• 42 • 1
l3lab/L1-1.5B-Short
2B • Updated
l3lab/all-distilroberta-v1-lr2e-4-bs256-nneg3-ml-ne2
Updated
• 15
l3lab/L1-Qwen-1.5B-Exact
2B • Updated
• 657 • 6
l3lab/L1-Qwen-1.5B-Max
2B • Updated
• 90 • 15
l3lab/ntp-mathlib-context-deepseek-coder-1.3b
Text Generation • Updated
• 70 • 3
l3lab/ntp-mathlib-st-deepseek-coder-1.3b
Text Generation • Updated
• 4
datasets 9
l3lab/miniCTX-v2
Viewer
• Updated
• 668 • 203 • 3
l3lab/miniCTX-v2-data
Updated
• 5
l3lab/Massive-Math-455K-Verified
Viewer
• Updated
• 455k • 96 • 1
l3lab/lean-premises
Updated
• 21 • 2
l3lab/miniCTX
Viewer
• Updated
• 662 • 292 • 3
l3lab/ntp-mathlib-instruct-context-fullproof
Viewer
• Updated
• 144k • 47 • 1
l3lab/ntp-mathlib-instruct-context
Viewer
• Updated
• 614k • 69 • 1
l3lab/ntp-mathlib
Viewer
• Updated
• 213k • 94 • 2
l3lab/ntp-mathlib-instruct-st
Viewer
• Updated
• 307k • 32