macadeliccc/magistrate-3.2-3b-it
Partial fine-tune vs macadeliccc/magistrate-3.2-3b-base. Partial change: 50% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Norms 28/57, MLP 42/84, Attention 56/112
1 derivatives checked
- mradermacher/magistrate-3.2-3b-it-GGUF: Same weights, converted