Portfolio of models, datasets and demos presented in the paper G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
PKU Machine Learning Group
PKU-ML
AI & ML interests
None yet
Organizations
models
8
PKU-ML/G1-Direct-SFT-3B
Text Generation
•
3B
•
Updated
•
17
PKU-ML/G1-Direct-SFT-7B
Text Generation
•
8B
•
Updated
PKU-ML/G1-CoT-SFT-7B
Text Generation
•
8B
•
Updated
PKU-ML/G1-CoT-SFT-3B
Text Generation
•
3B
•
Updated
•
18
PKU-ML/G1-7B
Text Generation
•
8B
•
Updated
•
50
•
2
PKU-ML/G1-Zero-7B
Text Generation
•
8B
•
Updated
•
2
PKU-ML/G1-Zero-3B
Text Generation
•
3B
•
Updated
•
17
PKU-ML/G1-3B
Text Generation
•
3B
•
Updated
•
53
•
1