0arch-io/kisoku-3b-sft
Full fine-tune vs 0arch-io/kisoku-3b-base. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 112/112
2 derivatives checked
- mradermacher/kisoku-3b-sft-i1-GGUF: Quantization
- mradermacher/kisoku-3b-sft-GGUF: Same weights, converted