core-3/kuno-royale-v2-7b
Full fine-tune vs SanjiWatsuki/Kunoichi-DPO-v2-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1
3 derivatives checked
- mradermacher/kuno-royale-v2-7b-i1-GGUF: Quantization
- mradermacher/kuno-royale-v2-7b-GGUF: Same weights, converted
- grimjim/zephyr-wizard-kuno-royale-BF16-merge-7B: Full fine-tune