Khetterman/AbominationScience-12B-v4
Full fine-tune vs Azazelle/MN-Halide-12b-v1.0. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 47/81, MLP 120/120, Attention 160/160
6 derivatives checked
- mradermacher/AbominationScience-12B-v4-i1-GGUF: Quantization
- mradermacher/AbominationScience-12B-v4-GGUF: Quantization
- mergekit-community/MN-Sappho-c-12B: Full fine-tune
- mergekit-community/MN-Hekate-Ekklesia-12B: Full fine-tune
- mergekit-community/MN-Sappho-m-12B: Full fine-tune
- mergekit-community/MN-Hekate-Geneteira-17B: Full fine-tune