Lewdiculous/Aura_Uncensored_l3_8B-GGUF-IQ-Imatrix
Adapter vs ResplendentAI/Aura_Llama3. ResplendentAI/Aura_Llama3 is a LoRA adapter, not full weights: rank 128, on q_proj, v_proj in 32 layers (64 adapted matrices). It modifies Lewdiculous/Aura_Uncensored_l3_8B-GGUF-IQ-Imatrix at load time.