backyardai/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B
Full fine-tune (fewer layers) vs Hastagaras/Jamet-8B-L3-MK.V-Blackroot. Hastagaras/Jamet-8B-L3-MK.V-Blackroot matches part of backyardai/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B (291 of its 642 tensors; the rest of backyardai/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B has no counterpart). On the shared part: Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 64/65, MLP 96/96, Attention 128/128, lm_head 0/1
3 derivatives checked
- backyardai/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-GGUF: Quantization
- mradermacher/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-i1-GGUF: Quantization
- mradermacher/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.