saishf/Aura-Uncensored-OAS-8B-L3
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 saishf/Aura-Uncensored-OAS-8B-L3 at load time.
4 derivatives checked
- mradermacher/Aura-Uncensored-OAS-8B-L3-i1-GGUF: Quantization
- mradermacher/Aura-Uncensored-OAS-8B-L3-GGUF: Same weights, converted
- featherless-ai-quants/saishf-Aura-Uncensored-OAS-8B-L3-GGUF: Quantization
- tensorblock/saishf_Aura-Uncensored-OAS-8B-L3-GGUF: Quantization