OliviaRossi/MiMo-Ornith-9B-AGSI
Full fine-tune vs XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 4/4, MLP 207/208, Attention 314/332, Norms 205/215
4 derivatives checked
- bartowski/OliviaRossi_MiMo-Ornith-9B-AGSI-GGUF: Same weights, converted
- mradermacher/MiMo-Ornith-9B-AGSI-i1-GGUF: Quantization
- OliviaRossi/OliviaRossi_MiMo-Ornith-9B-AGSI-GGUF: Same weights, converted
- mradermacher/MiMo-Ornith-9B-AGSI-GGUF: Same weights, converted