{
  "add_skip_keys": true,
  "dequantize_fp32": false,
  "dynamic_loss_threshold": null,
  "group_size": 0,
  "hadamard_group_size": 256,
  "is_integer": true,
  "is_training": false,
  "minimum_allowed_numel": 16384,
  "modules_dtype_dict": {},
  "modules_quant_config": {},
  "modules_to_not_convert": [
    ".proj_out",
    ".t_embedder",
    ".txt_out",
    ".img_out",
    "time_modulation",
    ".context_embedder",
    "patch_emb",
    "time_embedder",
    "scale_shift_table",
    "norm_out",
    "norm_q",
    ".vid_in",
    "norm1",
    ".norm_out",
    ".vid_out",
    ".condition_embedder",
    "norm",
    "patch_embedding",
    "lm_head",
    "norm_post_ffn",
    "norm_post_attn",
    ".img_in",
    ".final_layer",
    ".txt_in",
    ".x_embedder",
    "time_text_embed",
    "router",
    ".y_embedder",
    "wte",
    "norm2",
    "norm_out_modulation",
    ".time_embed",
    "norm_k",
    "multi_modal_projector",
    "patch_embed",
    ".emb_in",
    ".emb_out"
  ],
  "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": "0.2.2",
  "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"
}