Nitral-Archive/Kunocchini-7b
Full fine-tune vs Epiculous/Fett-uccine-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
4 derivatives checked
- mradermacher/Kunocchini-GGUF: Same weights, converted
- mradermacher/Kunocchini-7b-i1-GGUF: Quantization
- mradermacher/Kunocchini-i1-GGUF: Quantization
- Nitral-Archive/Pasta-PrimaMaid-7b: Full fine-tune