| { |
| "add_skip_keys": false, |
| "dequantize_fp32": false, |
| "dynamic_loss_threshold": null, |
| "group_size": 0, |
| "is_integer": true, |
| "is_training": false, |
| "modules_dtype_dict": {}, |
| "modules_quant_config": {}, |
| "modules_to_not_convert": [ |
| ".img_out", |
| ".proj_out", |
| ".emb_in", |
| ".final_layer", |
| "patch_embed", |
| ".time_embed", |
| "multi_modal_projector", |
| ".condition_embedder", |
| ".t_embedder", |
| "wte", |
| "lm_head", |
| ".txt_out", |
| "time_text_embed", |
| ".context_embedder", |
| ".txt_in", |
| ".emb_out", |
| ".norm_out", |
| ".img_in", |
| ".vid_in", |
| ".x_embedder", |
| "patch_embedding", |
| "patch_emb", |
| ".vid_out", |
| ".y_embedder", |
| "layers.0.adaLN_mlp_ln.weight", |
| "layers.0.adaLN_sa_ln.weight", |
| "layers.0.self_attention.norm_k.weight", |
| "layers.0.self_attention.norm_q.weight", |
| "layers.1.adaLN_mlp_ln.weight", |
| "layers.1.adaLN_sa_ln.weight", |
| "layers.1.self_attention.norm_k.weight", |
| "layers.1.self_attention.norm_q.weight", |
| "layers.10.adaLN_mlp_ln.weight", |
| "layers.10.adaLN_sa_ln.weight", |
| "layers.10.self_attention.norm_k.weight", |
| "layers.10.self_attention.norm_q.weight", |
| "layers.11.adaLN_mlp_ln.weight", |
| "layers.11.adaLN_sa_ln.weight", |
| "layers.11.self_attention.norm_k.weight", |
| "layers.11.self_attention.norm_q.weight", |
| "layers.12.adaLN_mlp_ln.weight", |
| "layers.12.adaLN_sa_ln.weight", |
| "layers.12.self_attention.norm_k.weight", |
| "layers.12.self_attention.norm_q.weight", |
| "layers.13.adaLN_mlp_ln.weight", |
| "layers.13.adaLN_sa_ln.weight", |
| "layers.13.self_attention.norm_k.weight", |
| "layers.13.self_attention.norm_q.weight", |
| "layers.14.adaLN_mlp_ln.weight", |
| "layers.14.adaLN_sa_ln.weight", |
| "layers.14.self_attention.norm_k.weight", |
| "layers.14.self_attention.norm_q.weight", |
| "layers.15.adaLN_mlp_ln.weight", |
| "layers.15.adaLN_sa_ln.weight", |
| "layers.15.self_attention.norm_k.weight", |
| "layers.15.self_attention.norm_q.weight", |
| "layers.16.adaLN_mlp_ln.weight", |
| "layers.16.adaLN_sa_ln.weight", |
| "layers.16.self_attention.norm_k.weight", |
| "layers.16.self_attention.norm_q.weight", |
| "layers.17.adaLN_mlp_ln.weight", |
| "layers.17.adaLN_sa_ln.weight", |
| "layers.17.self_attention.norm_k.weight", |
| "layers.17.self_attention.norm_q.weight", |
| "layers.18.adaLN_mlp_ln.weight", |
| "layers.18.adaLN_sa_ln.weight", |
| "layers.18.self_attention.norm_k.weight", |
| "layers.18.self_attention.norm_q.weight", |
| "layers.19.adaLN_mlp_ln.weight", |
| "layers.19.adaLN_sa_ln.weight", |
| "layers.19.self_attention.norm_k.weight", |
| "layers.19.self_attention.norm_q.weight", |
| "layers.2.adaLN_mlp_ln.weight", |
| "layers.2.adaLN_sa_ln.weight", |
| "layers.2.self_attention.norm_k.weight", |
| "layers.2.self_attention.norm_q.weight", |
| "layers.20.adaLN_mlp_ln.weight", |
| "layers.20.adaLN_sa_ln.weight", |
| "layers.20.self_attention.norm_k.weight", |
| "layers.20.self_attention.norm_q.weight", |
| "layers.21.adaLN_mlp_ln.weight", |
| "layers.21.adaLN_sa_ln.weight", |
| "layers.21.self_attention.norm_k.weight", |
| "layers.21.self_attention.norm_q.weight", |
| "layers.22.adaLN_sa_ln.weight", |
| "layers.3.adaLN_mlp_ln.weight", |
| "layers.3.adaLN_sa_ln.weight", |
| "layers.3.self_attention.norm_k.weight", |
| "layers.3.self_attention.norm_q.weight", |
| "layers.4.adaLN_mlp_ln.weight", |
| "layers.4.adaLN_sa_ln.weight", |
| "layers.4.self_attention.norm_k.weight", |
| "layers.4.self_attention.norm_q.weight", |
| "layers.5.adaLN_mlp_ln.weight", |
| "layers.5.adaLN_sa_ln.weight", |
| "layers.5.self_attention.norm_k.weight", |
| "layers.5.self_attention.norm_q.weight", |
| "layers.6.adaLN_mlp_ln.weight", |
| "layers.6.adaLN_sa_ln.weight", |
| "layers.6.self_attention.norm_k.weight", |
| "layers.6.self_attention.norm_q.weight", |
| "layers.7.adaLN_mlp_ln.weight", |
| "layers.7.adaLN_sa_ln.weight", |
| "layers.7.self_attention.norm_k.weight", |
| "layers.7.self_attention.norm_q.weight", |
| "layers.8.adaLN_mlp_ln.weight", |
| "layers.8.adaLN_sa_ln.weight", |
| "layers.8.self_attention.norm_k.weight", |
| "layers.8.self_attention.norm_q.weight", |
| "layers.9.adaLN_mlp_ln.weight", |
| "layers.9.adaLN_sa_ln.weight", |
| "layers.9.self_attention.norm_k.weight", |
| "layers.9.self_attention.norm_q.weight", |
| "time_embedding.linear_1.weight", |
| "time_embedding.linear_2.weight", |
| "x_embedder.proj.weight", |
| "layers.22.adaLN_mlp_ln.weight", |
| "layers.22.self_attention.norm_k.weight", |
| "layers.22.self_attention.norm_q.weight", |
| "layers.23.adaLN_mlp_ln.weight", |
| "layers.23.adaLN_sa_ln.weight", |
| "layers.23.self_attention.norm_k.weight", |
| "layers.23.self_attention.norm_q.weight", |
| "layers.24.adaLN_mlp_ln.weight", |
| "layers.24.adaLN_sa_ln.weight", |
| "layers.24.self_attention.norm_k.weight", |
| "layers.24.self_attention.norm_q.weight", |
| "layers.25.adaLN_mlp_ln.weight", |
| "layers.25.adaLN_sa_ln.weight", |
| "layers.25.self_attention.norm_k.weight", |
| "layers.25.self_attention.norm_q.weight", |
| "layers.26.adaLN_mlp_ln.weight", |
| "layers.26.adaLN_sa_ln.weight", |
| "layers.26.self_attention.norm_k.weight", |
| "layers.26.self_attention.norm_q.weight", |
| "layers.27.adaLN_mlp_ln.weight", |
| "layers.27.adaLN_sa_ln.weight", |
| "layers.27.self_attention.norm_k.weight", |
| "layers.27.self_attention.norm_q.weight", |
| "layers.28.adaLN_mlp_ln.weight", |
| "layers.28.adaLN_sa_ln.weight", |
| "layers.28.self_attention.norm_k.weight", |
| "layers.28.self_attention.norm_q.weight", |
| "layers.29.adaLN_mlp_ln.weight", |
| "layers.29.adaLN_sa_ln.weight", |
| "layers.29.self_attention.norm_k.weight", |
| "layers.29.self_attention.norm_q.weight", |
| "layers.30.adaLN_mlp_ln.weight", |
| "layers.30.adaLN_sa_ln.weight", |
| "layers.30.self_attention.norm_k.weight", |
| "layers.30.self_attention.norm_q.weight", |
| "layers.31.adaLN_mlp_ln.weight", |
| "layers.31.adaLN_sa_ln.weight", |
| "layers.31.self_attention.norm_k.weight", |
| "layers.31.self_attention.norm_q.weight", |
| "layers.32.adaLN_mlp_ln.weight", |
| "layers.32.adaLN_sa_ln.weight", |
| "layers.32.self_attention.norm_k.weight", |
| "layers.32.self_attention.norm_q.weight", |
| "layers.33.adaLN_mlp_ln.weight", |
| "layers.33.adaLN_sa_ln.weight", |
| "layers.33.self_attention.norm_k.weight", |
| "layers.33.self_attention.norm_q.weight", |
| "layers.34.adaLN_mlp_ln.weight", |
| "layers.34.adaLN_sa_ln.weight", |
| "layers.34.self_attention.norm_k.weight", |
| "layers.34.self_attention.norm_q.weight", |
| "layers.35.adaLN_mlp_ln.weight", |
| "layers.35.adaLN_sa_ln.weight", |
| "layers.35.self_attention.norm_k.weight", |
| "layers.35.self_attention.norm_q.weight" |
| ], |
| "modules_to_not_use_matmul": [], |
| "non_blocking": false, |
| "quant_conv": false, |
| "quant_embedding": false, |
| "quant_method": "sdnq", |
| "quantization_device": null, |
| "quantized_matmul_dtype": null, |
| "return_device": null, |
| "sdnq_version": "0.1.9", |
| "svd_rank": 32, |
| "svd_steps": 8, |
| "use_dynamic_quantization": false, |
| "use_grad_ckpt": true, |
| "use_quantized_matmul": true, |
| "use_quantized_matmul_conv": false, |
| "use_static_quantization": true, |
| "use_stochastic_rounding": false, |
| "use_svd": false, |
| "weights_dtype": "uint4" |
| } |
|
|
