mradermacher/cem-v0.1-GGUF
Adapter vs beratcmn/cem-v0.1. beratcmn/cem-v0.1 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 28 layers (196 adapted matrices). It modifies mradermacher/cem-v0.1-GGUF at load time.