softwareweaver/Twilight-Large-123B
Full fine-tune vs TheDrummer/Behemoth-123B-v1. Fine-tune: 100% of the weights changed, across 88 of 88 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 64/177, MLP 264/264, Attention 352/352
1 derivatives checked
- mradermacher/Twilight-Large-123B-i1-GGUF: Quantization