Replace whole-word `LossKwargs` with `TransformersKwargs` in modeling*.py ca4d45e verified Harsh1729 commited on Sep 26, 2025
Initial upload from /leonardo_work/AIFAC_L01_028/hraj0000/megatron_lm_reference/converted_checkpoints/1.7b_data-MixtureVitae-300BT-80BT/hf/iter_0019377 1d796fe verified Harsh1729 commited on Sep 22, 2025