A series of reasoning models trained with SFT, followed by DPO and a GRPO variant as well as SEMPER during the RL phase. It performs surprisingly well given the low number of examples (10K) during the final RL phase.
Specs
Params32B
LicenseEXAONE AI Model License Agreement 1.1 - NC
Tags
modelsmodels/llmsmodels/llms/reasoningmultilingualartifacts/8
Related Models
