aisingapore/Nemotron-SEA-LION-v4.8-120B-A12B

Full fine-tune vs aisingapore/Nemotron-SEA-LION-v4.8-120B-A12B-Base. Fine-tune: 99% of the weights changed, across 88 of 88 layers.

Tensors changed: Embeddings 1/1, other 320/360, Norms 84/129, MLP 2352/2395, Attention 32/32, lm_head 1/1

1 derivatives checked