grimjim/kunoichi-lemon-royale-v3-32K-7B
Full fine-tune vs grimjim/kunoichi-lemon-royale-v2-32K-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 12/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- featherless-ai-quants/grimjim-kunoichi-lemon-royale-v3-32K-7B-GGUF: Quantization
- grimjim/kunoichi-lemon-royale-v3-32K-7B-GGUF: Quantization
- mradermacher/kunoichi-lemon-royale-v3-32K-7B-GGUF: Same weights, converted