djuna/MN-Miuryra-18B
Full fine-tune (fewer layers) vs DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-MADNESS. DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-MADNESS matches part of djuna/MN-Miuryra-18B (363 of its 561 tensors; the rest of djuna/MN-Miuryra-18B has no counterpart). On the shared part: Fine-tune: 95% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 0/1, Embeddings 1/1, Norms 71/81, MLP 120/120, Attention 160/160
2 derivatives checked
- mradermacher/MN-Miuryra-18B-i1-GGUF: Quantization
- mradermacher/MN-Miuryra-18B-GGUF: Quantization