snuperh/AllInOne-XL-V12.5

Full fine-tune vs Laxhar/noobai-XL-1.0. Fine-tune: 98% of the weights changed, across 12 of 12 layers.

Tensors changed: Embeddings 590/590, other 534/662, Attention 700/716, Norms 442/546

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse