nbeerbower/bruphin-epsilon
Full fine-tune vs BarryFutureman/WildMarcoroni-Variant1-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 13/65, MLP 93/96, Attention 124/128, lm_head 1/1
2 derivatives checked
- mradermacher/bruphin-epsilon-GGUF: Same weights, converted
- nbeerbower/bruphin-kappa: Full fine-tune