FallenMerick/MN-Violet-Lotus-12B
Full fine-tune vs Epiculous/Violet_Twilight-v0.2. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 47/81, MLP 120/120, Attention 160/160
13 derivatives checked
- mradermacher/MN-Violet-Lotus-12B-GGUF: Quantization
- mradermacher/MN-Violet-Lotus-12B-i1-GGUF: Quantization
- backyardai/MN-Violet-Lotus-12B-GGUF: Quantization
- MaziyarPanahi/MN-Violet-Lotus-12B-GGUF: Same weights, converted
- hammerai/MN-Violet-Lotus-12B-GGUF: Quantization
- hobaratio/MN-Violet-Lotus-12B-mlx-8Bit: Quantization
- meganovaai/MN-Violet-Lotus-12B-AWQ: Quantization
- skelethor209/MN-Violet-Lotus-12B-mlx-4Bit: Quantization
- WasamiKirua/Hexis-Vesper-12B: Full fine-tune
- Ateron/Lotus-Magpic: Full fine-tune
- Vortex5/Gilded-Tempest-12B: Full fine-tune
- Sorihon/MN-Violet-Lotus-12B-Heretic: Abliterated
- MrRikyz/Violet-Eclipse-12B: Full fine-tune
1 other repos hold byte-for-byte identical weight files.