aciklab/kubernetes-ai-lora
Adapter vs unsloth/gemma-3-12b-it-qat-bnb-4bit. aciklab/kubernetes-ai-lora is a LoRA adapter, not full weights: rank 8, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 48 layers (417 adapted matrices). It modifies unsloth/gemma-3-12b-it-qat-bnb-4bit at load time.
1 derivatives checked
- aciklab/kubernetes-ai-GGUF: Adapter