ResplendentAI/Aura_Uncensored_l3_8B
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 ResplendentAI/Aura_Uncensored_l3_8B at load time.
6 derivatives checked
- mradermacher/Aura_Uncensored_l3_8B-GGUF: Quantization
- Azazelle/L3-RP_io: Partial fine-tune
- nbeerbower/llama-3-aura-bophades-8B: Full fine-tune
- Fischerboot/mergekit-slerp-awrvish: Partial fine-tune
- Azazelle/Llama-3-8B-contaminated-roleplay: Full fine-tune
- ChaoticNeutrals/Puppy_Purpose_0.69: Full fine-tune