btaskel/Illustrious-XL-v2.0-GGUF
Quantization (fewer layers) vs OnomaAIResearch/Illustrious-XL-v2.0. btaskel/Illustrious-XL-v2.0-GGUF matches part of OnomaAIResearch/Illustrious-XL-v2.0 (1548 of its 2515 tensors; the rest of OnomaAIResearch/Illustrious-XL-v2.0 has no counterpart). On the shared part: btaskel/Illustrious-XL-v2.0-GGUF is a GGUF quantization (Q8_0) of the same weights: 901 tensors match exactly and 647 within quantization error.
Tensors changed: other 0/463, Norms 0/442, Attention 0/640, Embeddings 0/3
1 derivatives checked
- thecakeisal1e/ily-scat-smear: Adapter