mradermacher/gemma-2-2b-dunsany-GGUF
Adapter vs neph1/gemma-2-2b-dunsany. neph1/gemma-2-2b-dunsany is a LoRA adapter, not full weights: rank 128, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 26 layers (182 adapted matrices). It modifies mradermacher/gemma-2-2b-dunsany-GGUF at load time.