mergekit-community/mergekit-slerp-zvrdvfy
Full fine-tune vs NousResearch/Hermes-2-Pro-Mistral-7B. Fine-tune: 94% of the weights changed, across 30 of 32 layers.
Tensors changed: Norms 12/65, MLP 90/96, Attention 120/128
1 derivatives checked
- MaziyarPanahi/mergekit-slerp-zvrdvfy-GGUF: Quantization
40 other repos hold byte-for-byte identical weight files.