Delta-Vector/Hamanasu-15B-Instruct
Full fine-tune vs Delta-Vector/Hamanasu-15B-R2-PT. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 0/81, MLP 120/120, Attention 160/160
3 derivatives checked
- mradermacher/Hamanasu-15B-Instruct-i1-GGUF: Quantization
- mradermacher/Hamanasu-15B-Instruct-GGUF: Quantization
- Delta-Vector/Hamanasu-15B-Adventure: Full fine-tune