mergekit-community/MN-Sappho-c-12B
Full fine-tune vs Khetterman/AbominationScience-12B-v4. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 44/81, MLP 120/120, Attention 160/160
3 derivatives checked
- mradermacher/MN-Sappho-c-12B-i1-GGUF: Quantization
- mradermacher/MN-Sappho-c-12B-GGUF: Quantization
- mergekit-community/MN-Sappho-jlcj-12B: Partial fine-tune