winterfeb/gemma-270m-ko-en-Q8_0-GGUF
Adapter vs winterfeb/gemma-270m-ko-en. winterfeb/gemma-270m-ko-en 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 18 layers (126 adapted matrices). It modifies winterfeb/gemma-270m-ko-en-Q8_0-GGUF at load time.