AthrvShrn/Socrates-Qwen3-8B-GGUF
Adapter vs AthrvShrn/Socrates-Qwen3-8B. AthrvShrn/Socrates-Qwen3-8B is a LoRA adapter, not full weights: rank 32, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 36 layers (252 adapted matrices). It modifies AthrvShrn/Socrates-Qwen3-8B-GGUF at load time.