mergekit-community/MN-Sappho-g2-12B
Full fine-tune vs DavidAU/MN-Dark-Planet-TITAN-12B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 38/81, MLP 120/120, Attention 160/160
1 derivatives checked
- mradermacher/MN-Sappho-g2-12B-GGUF: Quantization