Laxhar/noobai-XL-0.77

Full fine-tune vs Laxhar/noobai-XL-0.75. Fine-tune: 97% of the weights changed, across 11 of 12 layers.

Tensors changed: Embeddings 571/590, other 534/662, Attention 700/716, Norms 442/546

1 derivatives checked

• Laxhar/noobai-XL-1.0: Full fine-tune

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

On the Hub · Downloads on Model Pulse