GRPO on math model using Multilinguality and Knowledge GRPO datasets. Checkpoint 1000 was remerged back with math model.

Downloads last month
19
Safetensors
Model size
2B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including JoanneJegou/GRPO_math_merge