AIDX-ktds/ktdsbaseLM-v0.13-onbased-llama3.1

Partial fine-tune vs meta-llama/Llama-3.1-8B-Instruct. Partial change: 87% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 14/65, MLP 96/96, Attention 128/128, lm_head 0/1

2 derivatives checked

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