yamatazen/MidnightMoon-16B
Partial fine-tune vs Elizezen/Himeyuri-v0.1-12B. Partial change: 64% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 24 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 49/81, MLP 72/120, Attention 96/160
2 derivatives checked
- mradermacher/MidnightMoon-16B-i1-GGUF: Quantization
- mradermacher/MidnightMoon-16B-GGUF: Quantization