Delta-Vector/Archaeo-32B
Full fine-tune vs Delta-Vector/Hamanasu-Magnum-QwQ-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 127/129, MLP 192/192, Attention 448/448
5 derivatives checked
- mradermacher/Archaeo-32B-i1-GGUF: Quantization
- mradermacher/Hamanasu-Magnum-Kunou-i1-GGUF: Quantization
- mradermacher/Hamanasu-Magnum-Kunou-GGUF: Quantization
- mradermacher/Archaeo-32B-GGUF: Quantization
- Delta-Vector/Archaeo-32B-KTO: LoRA-style