yamatazen/EtherealAurora-12B-v2
Full fine-tune vs natong19/Mistral-Nemo-Instruct-2407-abliterated. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 81/81, MLP 120/120, Attention 160/160, lm_head 1/1
7 derivatives checked
- BasedAGI/EtherealAurora-12B-v2-i1-GGUF: Quantization
- mradermacher/EtherealAurora-12B-v2-i1-GGUF: Quantization
- DevQuasar-6/yamatazen.EtherealAurora-12B-v2-GGUF: Same weights, converted
- mradermacher/EtherealAurora-12B-v2-GGUF: Quantization
- tensorblock/yamatazen_EtherealAurora-12B-v2-GGUF: Quantization
- Marcjoni/AbyssSynth-12B: Full fine-tune
- Sorihon/EtherealAurora-12B-v2-Heretic: Abliterated