RL trained models and datasets for instruction-following
AI & ML interests
None defined yet.
Recent Activity
View all activity
Collections
6
models
66

THU-KEG/LongWriter-Zero-32B
Text Generation
•
Updated
•
85
•
23

THU-KEG/IF-Verifier-7B
Text2Text Generation
•
Updated
•
24

THU-KEG/R1-Distill-Qwen-7B-VerIF
Text2Text Generation
•
Updated
•
17

THU-KEG/TULU3-VerIF
Text2Text Generation
•
Updated
•
20

THU-KEG/AdaptThink-7B-delta0.05
Updated
•
120
•
1

THU-KEG/AdaptThink-1.5B-delta0.1
Updated
•
21
•
2

THU-KEG/AdaptThink-1.5B-delta0.075
Updated
•
70

THU-KEG/AdaptThink-1.5B-delta0.02
Updated
•
55

THU-KEG/AdaptThink-1.5B-delta0.01
Updated
•
49
•
1

THU-KEG/AdaptThink-1.5B-delta0
Updated
•
81
datasets
18
THU-KEG/Arena-Write
Viewer
•
Updated
•
595
•
70
•
1
THU-KEG/LongWriter-Zero-RLData
Viewer
•
Updated
•
8.61k
•
72
•
9
THU-KEG/LongStory
Viewer
•
Updated
•
5.28k
•
11
•
1
THU-KEG/IF-Verifier-Data
Viewer
•
Updated
•
131k
•
147
•
1
THU-KEG/VerInstruct
Viewer
•
Updated
•
27.5k
•
194
•
1
THU-KEG/MM-Math-Align
Viewer
•
Updated
•
4.02k
•
306
•
1
THU-KEG/AgentIF
Updated
•
102
•
4
THU-KEG/ReaRAG-20k
Viewer
•
Updated
•
20.5k
•
32
•
1
THU-KEG/MRCEval
Viewer
•
Updated
•
2.1k
•
27
THU-KEG/IFBench
Viewer
•
Updated
•
444
•
40
•
5