{ "add_skip_keys": false, "dequantize_fp32": false, "dynamic_loss_threshold": null, "group_size": 0, "hadamard_group_size": 128, "is_integer": true, "is_training": false, "modules_dtype_dict": {}, "modules_quant_config": {}, "modules_to_not_convert": [ "llm_cond_norm.weight", "embed_image_indicator.weight", "layers.0.attention.norm_q.weight", "layers.0.attention.norm_k.weight", "layers.0.attention_norm1.weight", "layers.0.ffn_norm1.weight", "layers.0.attention_norm2.weight", "layers.0.ffn_norm2.weight", "layers.1.attention.norm_q.weight", "layers.1.attention.norm_k.weight", "layers.1.attention_norm1.weight", "layers.1.ffn_norm1.weight", "layers.1.attention_norm2.weight", "layers.1.ffn_norm2.weight", "layers.2.attention.norm_q.weight", "layers.2.attention.norm_k.weight", "layers.2.attention_norm1.weight", "layers.2.ffn_norm1.weight", "layers.2.attention_norm2.weight", "layers.2.ffn_norm2.weight", "layers.3.attention.norm_q.weight", "layers.3.attention.norm_k.weight", "layers.3.attention_norm1.weight", "layers.3.ffn_norm1.weight", "layers.3.attention_norm2.weight", "layers.3.ffn_norm2.weight", "layers.4.attention.norm_q.weight", "layers.4.attention.norm_k.weight", "layers.4.attention_norm1.weight", "layers.4.ffn_norm1.weight", "layers.4.attention_norm2.weight", "layers.4.ffn_norm2.weight", "layers.5.attention.norm_q.weight", "layers.5.attention.norm_k.weight", "layers.5.attention_norm1.weight", "layers.5.ffn_norm1.weight", "layers.5.attention_norm2.weight", "layers.5.ffn_norm2.weight", "layers.6.attention.norm_q.weight", "layers.6.attention.norm_k.weight", "layers.6.attention_norm1.weight", "layers.6.ffn_norm1.weight", "layers.6.attention_norm2.weight", "layers.6.ffn_norm2.weight", "layers.7.attention.norm_q.weight", "layers.7.attention.norm_k.weight", "layers.7.attention_norm1.weight", "layers.7.ffn_norm1.weight", "layers.7.attention_norm2.weight", "layers.7.ffn_norm2.weight", "layers.8.attention.norm_q.weight", "layers.8.attention.norm_k.weight", "layers.8.attention_norm1.weight", "layers.8.ffn_norm1.weight", "layers.8.attention_norm2.weight", "layers.8.ffn_norm2.weight", "layers.9.attention.norm_q.weight", "layers.9.attention.norm_k.weight", "layers.9.attention_norm1.weight", "layers.9.ffn_norm1.weight", "layers.9.attention_norm2.weight", "layers.9.ffn_norm2.weight", "layers.10.attention.norm_q.weight", "layers.10.attention.norm_k.weight", "layers.10.attention_norm1.weight", "layers.10.ffn_norm1.weight", "layers.10.attention_norm2.weight", "layers.10.ffn_norm2.weight", "layers.11.attention.norm_q.weight", "layers.11.attention.norm_k.weight", "layers.11.attention_norm1.weight", "layers.11.ffn_norm1.weight", "layers.11.attention_norm2.weight", "layers.11.ffn_norm2.weight", "layers.12.attention.norm_q.weight", "layers.12.attention.norm_k.weight", "layers.12.attention_norm1.weight", "layers.12.ffn_norm1.weight", "layers.12.attention_norm2.weight", "layers.12.ffn_norm2.weight", "layers.13.attention.norm_q.weight", "layers.13.attention.norm_k.weight", "layers.13.attention_norm1.weight", "layers.13.ffn_norm1.weight", "layers.13.attention_norm2.weight", "layers.13.ffn_norm2.weight", "layers.14.attention.norm_q.weight", "layers.14.attention.norm_k.weight", "layers.14.attention_norm1.weight", "layers.14.ffn_norm1.weight", "layers.14.attention_norm2.weight", "layers.14.ffn_norm2.weight", "layers.15.attention.norm_q.weight", "layers.15.attention.norm_k.weight", "layers.15.attention_norm1.weight", "layers.15.ffn_norm1.weight", "layers.15.attention_norm2.weight", "layers.15.ffn_norm2.weight", "layers.16.attention.norm_q.weight", "layers.16.attention.norm_k.weight", "layers.16.attention_norm1.weight", "layers.16.ffn_norm1.weight", "layers.16.attention_norm2.weight", "layers.16.ffn_norm2.weight", "layers.17.attention.norm_q.weight", "layers.17.attention.norm_k.weight", "layers.17.attention_norm1.weight", "layers.17.ffn_norm1.weight", "layers.17.attention_norm2.weight", "layers.17.ffn_norm2.weight", "layers.18.attention.norm_q.weight", "layers.18.attention.norm_k.weight", "layers.18.attention_norm1.weight", "layers.18.ffn_norm1.weight", "layers.18.attention_norm2.weight", "layers.18.ffn_norm2.weight", "layers.19.attention.norm_q.weight", "layers.19.attention.norm_k.weight", "layers.19.attention_norm1.weight", "layers.19.ffn_norm1.weight", "layers.19.attention_norm2.weight", "layers.19.ffn_norm2.weight", "layers.20.attention.norm_q.weight", "layers.20.attention.norm_k.weight", "layers.20.attention_norm1.weight", "layers.20.ffn_norm1.weight", "layers.20.attention_norm2.weight", "layers.20.ffn_norm2.weight", "layers.21.attention.norm_q.weight", "layers.21.attention.norm_k.weight", "layers.21.attention_norm1.weight", "layers.21.ffn_norm1.weight", "layers.21.attention_norm2.weight", "layers.21.ffn_norm2.weight", "layers.22.attention.norm_q.weight", "layers.22.attention.norm_k.weight", "layers.22.attention_norm1.weight", "layers.22.ffn_norm1.weight", "layers.22.attention_norm2.weight", "layers.22.ffn_norm2.weight", "layers.23.attention.norm_q.weight", "layers.23.attention.norm_k.weight", "layers.23.attention_norm1.weight", "layers.23.ffn_norm1.weight", "layers.23.attention_norm2.weight", "layers.23.ffn_norm2.weight", "layers.24.attention.norm_q.weight", "layers.24.attention.norm_k.weight", "layers.24.attention_norm1.weight", "layers.24.ffn_norm1.weight", "layers.24.attention_norm2.weight", "layers.24.ffn_norm2.weight", "layers.25.attention.norm_q.weight", "layers.25.attention.norm_k.weight", "layers.25.attention_norm1.weight", "layers.25.ffn_norm1.weight", "layers.25.attention_norm2.weight", "layers.25.ffn_norm2.weight", "layers.26.attention.norm_q.weight", "layers.26.attention.norm_k.weight", "layers.26.attention_norm1.weight", "layers.26.ffn_norm1.weight", "layers.26.attention_norm2.weight", "layers.26.ffn_norm2.weight", "layers.27.attention.norm_q.weight", "layers.27.attention.norm_k.weight", "layers.27.attention_norm1.weight", "layers.27.ffn_norm1.weight", "layers.27.attention_norm2.weight", "layers.27.ffn_norm2.weight", "layers.28.attention.norm_q.weight", "layers.28.attention.norm_k.weight", "layers.28.attention_norm1.weight", "layers.28.ffn_norm1.weight", "layers.28.attention_norm2.weight", "layers.28.ffn_norm2.weight", "layers.29.attention.norm_q.weight", "layers.29.attention.norm_k.weight", "layers.29.attention_norm1.weight", "layers.29.ffn_norm1.weight", "layers.29.attention_norm2.weight", "layers.29.ffn_norm2.weight", "layers.30.attention.norm_q.weight", "layers.30.attention.norm_k.weight", "layers.30.attention_norm1.weight", "layers.30.ffn_norm1.weight", "layers.30.attention_norm2.weight", "layers.30.ffn_norm2.weight", "layers.31.attention.norm_q.weight", "layers.31.attention.norm_k.weight", "layers.31.attention_norm1.weight", "layers.31.ffn_norm1.weight", "layers.31.attention_norm2.weight", "layers.31.ffn_norm2.weight", "layers.32.attention.norm_q.weight", "layers.32.attention.norm_k.weight", "layers.32.attention_norm1.weight", "layers.32.ffn_norm1.weight", "layers.32.attention_norm2.weight", "layers.32.ffn_norm2.weight", "layers.33.attention.norm_q.weight", "layers.33.attention.norm_k.weight", "layers.33.attention_norm1.weight", "layers.33.ffn_norm1.weight", "layers.33.attention_norm2.weight", "layers.33.ffn_norm2.weight" ], "modules_to_not_use_matmul": [], "non_blocking": false, "quant_conv": false, "quant_embedding": false, "quant_method": "sdnq", "quantization_device": "cuda", "quantized_matmul_dtype": null, "return_device": "cpu", "sdnq_version": "0.1.9", "svd_rank": 32, "svd_steps": 8, "use_dynamic_quantization": false, "use_grad_ckpt": true, "use_hadamard": false, "use_quantized_matmul": false, "use_quantized_matmul_conv": false, "use_static_quantization": true, "use_stochastic_rounding": false, "use_svd": false, "weights_dtype": "uint4" }