This is Nvidia's Nemotron Cascade 2 pruned down from 128 to 96 experts. The model is very capable but mathematics took a little hit after the pruning.

This was pruned with a self designed custom zero shot pruning method.

Downloads last month
52
Safetensors
Model size
24B params
Tensor type
F32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for blascotobasco/Nemotron-Cascade-2-96E-A3B

Finetuned
(13)
this model
Quantizations
1 model