grimjim/kunoichi-lemon-royale-hamansu-v1-32k-7B
Full fine-tune vs Delta-Vector/Hamanasu-7B-instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
2 derivatives checked
- mradermacher/kunoichi-lemon-royale-hamansu-v1-32k-7B-i1-GGUF: Quantization
- mradermacher/kunoichi-lemon-royale-hamansu-v1-32k-7B-GGUF: Same weights, converted