bamec66557/MISCHIEVOUS-12B
Full fine-tune vs ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 43/81, MLP 120/120, Attention 160/160
4 derivatives checked
- MaziyarPanahi/MISCHIEVOUS-12B-GGUF: Same weights, converted
- mradermacher/MISCHIEVOUS-12B-GGUF: Quantization
- bamec66557/MISCHIEVOUS-12B-Mix_0.1v: Full fine-tune
- bamec66557/MISCHIEVOUS-12B-Mix_0.2v: Full fine-tune