ResplendentAI/Kei_Llama3_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/Kei_Llama3_8B at load time.
4 derivatives checked
- mradermacher/Kei_Llama3_8B-i1-GGUF: Quantization
- featherless-ai-quants/ResplendentAI-Kei_Llama3_8B-GGUF: Quantization
- mradermacher/Kei_Llama3_8B-GGUF: Quantization
- jeiku/Average_Normie_l3_v0_8B: Full fine-tune