prithivMLmods/Evac-Opus-14B-Exp
Full fine-tune vs prithivMLmods/Elita-1. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 88/97, MLP 144/144, Attention 336/336
3 derivatives checked
- mradermacher/Evac-Opus-14B-Exp-i1-GGUF: Quantization
- DevQuasar-2/prithivMLmods.Evac-Opus-14B-Exp-GGUF: Same weights, converted
- mradermacher/Evac-Opus-14B-Exp-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.