icefog72/IceSakeRP-7b
Full fine-tune vs Ppoyaa/KunoichiVerse-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 96/96, Attention 128/128, Norms 65/65, Embeddings 1/1, lm_head 1/1
2 derivatives checked
- mradermacher/IceSakeRP-7b-i1-GGUF: Quantization
- icefog72/IceSakeRPTrainingTestV1-7b: LoRA-style