Collection of LLMs continually post-trained via offline GRPO to enhance mathematical reasoning capabilities.
AI & ML interests
None defined yet.
Recent Activity
models
6
KRAFTON/OpenThinker2-Offline-GRPO-7B
8B
•
Updated
•
5
•
3
KRAFTON/AceReason-Nemotron-1.1-Offline-GRPO-7B
8B
•
Updated
•
3
•
3
KRAFTON/OpenThinker3-Offline-GRPO-7B
8B
•
Updated
•
3
•
5
KRAFTON/KORani-v1-13B
Text Generation
•
Updated
•
10
•
7
KRAFTON/KORani-v2-13B
Text Generation
•
Updated
•
32
•
4
KRAFTON/KORani-v3-13B
Text Generation
•
Updated
•
914
•
22
datasets
0
None public yet