Skill

kermt-pretrain-scratch

Created by nvidia

Version 392ab8ab2587345a9d86240967f666bd59ac82ca

Overview

Pretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches pretrain_ddp.py inside the kermt container (detached for long runs). Unlike kermt-continue-pretrain, no starting checkpoint is loaded — the model is randomly initialized.

Source/credit

All skills