L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
L3 Lab
university
AI & ML interests
None defined yet.
Recent Activity
models
11

l3lab/L1-Qwen3-8B-Max
8B
•
Updated
•
39

l3lab/L1-Qwen3-8B-Exact
8B
•
Updated
•
3

l3lab/L1-Qwen-7B-Max
8B
•
Updated
•
41

l3lab/L1-Qwen-7B-Exact
8B
•
Updated
•
4

l3lab/L1-1.5B-Short
2B
•
Updated
•
2

l3lab/all-distilroberta-v1-lr2e-4-bs256-nneg3-ml-ne2
Updated
•
11

l3lab/L1-Qwen-1.5B-Exact
2B
•
Updated
•
2.68k
•
6

l3lab/L1-Qwen-1.5B-Max
2B
•
Updated
•
1.94k
•
16

l3lab/ntp-mathlib-context-deepseek-coder-1.3b
Text Generation
•
Updated
•
5
•
3

l3lab/ntp-mathlib-st-deepseek-coder-1.3b
Text Generation
•
Updated
•
6
datasets
9
l3lab/miniCTX-v2
Viewer
•
Updated
•
668
•
139
•
2
l3lab/miniCTX-v2-data
Updated
•
15
l3lab/Massive-Math-455K-Verified
Viewer
•
Updated
•
455k
•
107
l3lab/lean-premises
Updated
•
14
•
1
l3lab/miniCTX
Viewer
•
Updated
•
662
•
86
•
3
l3lab/ntp-mathlib-instruct-context-fullproof
Viewer
•
Updated
•
144k
•
24
•
1
l3lab/ntp-mathlib-instruct-context
Viewer
•
Updated
•
614k
•
58
•
1
l3lab/ntp-mathlib
Viewer
•
Updated
•
213k
•
77
•
2
l3lab/ntp-mathlib-instruct-st
Viewer
•
Updated
•
307k
•
36