Aurore-Reveil/Koto-Small-7B-IT
Full fine-tune vs allura-org/Koto-Small-7B-PT. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 67/73, MLP 108/108, Attention 252/252, lm_head 1/1
6 derivatives checked
- bartowski/Aurore-Reveil_Koto-Small-7B-IT-GGUF: Same weights, converted
- mradermacher/Koto-Small-7B-IT-i1-GGUF: Quantization
- mradermacher/Koto-Small-7B-IT-GGUF: Same weights, converted
- DevQuasar/Aurore-Reveil.Koto-Small-7B-IT-GGUF: Same weights, converted
- Mawdistical/Kuwutu-7B: LoRA-style
- Mawdistical/Kuwutu-Lite-7B: LoRA-style
1 other repos hold byte-for-byte identical weight files.