TheOneWhoWill/Coding-Monkey-Gemma-GGUF
Adapter vs TheOneWhoWill/Coding-Monkey-Gemma. TheOneWhoWill/Coding-Monkey-Gemma is a LoRA adapter, not full weights: rank 16, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 48 layers (328 adapted matrices). It modifies TheOneWhoWill/Coding-Monkey-Gemma-GGUF at load time.