mergekit-community/TopEvolution
Full fine-tune vs NousResearch/Hermes-2-Pro-Mistral-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 49/65, MLP 96/96, Attention 128/128
2 derivatives checked
- MaziyarPanahi/TopEvolution-GGUF: Quantization
- mergekit-community/TopEvolution-DPO-32K: Full fine-tune