yamatazen/KnowledgeCore-12B
Partial fine-tune vs PocketDoc/Dans-PersonalityEngine-V1.1.0-12b. Partial change: 78% of the weights changed (attention, mlp, norms), in 40 of 40 layers.
Tensors changed: Norms 40/81, MLP 88/120, Attention 158/160
2 derivatives checked
- mradermacher/KnowledgeCore-12B-i1-GGUF: Quantization
- mradermacher/KnowledgeCore-12B-GGUF: Quantization