Luni/StarDust-12b-v2
Full fine-tune vs Gryphe/Pantheon-RP-1.6-12b-Nemo. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 37/81, MLP 120/120, Attention 160/160, lm_head 1/1
6 derivatives checked
- bartowski/StarDust-12b-v2-GGUF: Same weights, converted
- mradermacher/StarDust-12b-v2-i1-GGUF: Quantization
- mradermacher/StarDust-12b-v2-GGUF: Quantization
- featherless-ai-quants/Luni-StarDust-12b-v2-GGUF: Quantization
- Tokerss/FandomDxd: LoRA-style
- mergekit-community/NM-StarUnleashed: Partial fine-tune