SicariusSicariiStuff/Wingless_Imp_8B
Full fine-tune vs SicariusSicariiStuff/Dusk_Rainbow. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
7 derivatives checked
- mradermacher/Wingless_Imp_8B-GGUF: Same weights, converted
- mradermacher/Wingless_Imp_8B-i1-GGUF: Quantization
- SicariusSicariiStuff/Wingless_Imp_8B_GGUF: Quantization
- SicariusSicariiStuff/Wingless_Imp_8B_iMatrix: Quantization
- SicariusSicariiStuff/Wingless_Imp_8B_GGUF_HA: Quantization
- SicariusSicariiStuff/Wingless_Imp_8B_Abliterated: Abliterated
- D1rtyB1rd/Wingless-Alice-RP-NSFW-8B: Full fine-tune