Vortex5/Amber-Starlight-12B
Full fine-tune vs DreadPoor/Strawberry_Smoothie-12B-Model_Stock. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160
4 derivatives checked
- mradermacher/Amber-Starlight-12B-i1-GGUF: Quantization
- mradermacher/Amber-Starlight-12B-GGUF: Quantization
- Vortex5/Ethereal-Stardust-12B: Full fine-tune
- Vortex5/Crimson-Constellation-12B: Full fine-tune