Edens-Gate/Chunky-Merge-V2
Full fine-tune vs Gryphe/Pantheon-RP-1.6.1-12b-Nemo. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 40/81, MLP 120/120, Attention 160/160
1 derivatives checked
- mradermacher/Chunky-Merge-V2-GGUF: Quantization