llama.cpp
7dee9ff5 - convert : use n_groups instead of hardcoded values in reshape (#18929)

Commit
62 days ago
convert : use n_groups instead of hardcoded values in reshape (#18929) * convert : use n_groups instead of hardcoded values in reshape This commit modifies the conversion script for NemotronHModel to use the 'n_groups' hyperparameter, and allow Python to calculate the the last dimension, using -1, when reshaping the 'mixer.norm.weight' tensor. * use self.n_group instead of self.hparams["n_groups"]
Author
Parents
Loading