text_encoder/quantization_config.json

{
  "add_skip_keys": false,
  "dequantize_fp32": false,
  "dynamic_loss_threshold": 0.01,
  "group_size": 0,
  "is_integer": true,
  "is_training": false,
  "modules_dtype_dict": {
    "int5": [
      "model.layers.2.mlp.down_proj.weight"
    ],
    "uint4": [
      "model.layers.0.mlp.down_proj.weight",
      "model.layers.0.mlp.gate_proj.weight",
      "model.layers.0.mlp.up_proj.weight",
      "model.layers.0.self_attn.k_proj.weight",
      "model.layers.0.self_attn.o_proj.weight",
      "model.layers.0.self_attn.q_proj.weight",
      "model.layers.0.self_attn.v_proj.weight",
      "model.layers.1.mlp.down_proj.weight",
      "model.layers.1.mlp.gate_proj.weight",
      "model.layers.1.mlp.up_proj.weight",
      "model.layers.1.self_attn.k_proj.weight",
      "model.layers.1.self_attn.o_proj.weight",
      "model.layers.1.self_attn.q_proj.weight",
      "model.layers.1.self_attn.v_proj.weight",
      "model.layers.2.mlp.gate_proj.weight",
      "model.layers.2.mlp.up_proj.weight",
      "model.layers.2.self_attn.k_proj.weight",
      "model.layers.2.self_attn.o_proj.weight",
      "model.layers.2.self_attn.q_proj.weight",
      "model.layers.2.self_attn.v_proj.weight",
      "model.layers.3.mlp.down_proj.weight",
      "model.layers.3.mlp.gate_proj.weight",
      "model.layers.3.mlp.up_proj.weight",
      "model.layers.3.self_attn.k_proj.weight",
      "model.layers.3.self_attn.o_proj.weight",
      "model.layers.3.self_attn.q_proj.weight",
      "model.layers.3.self_attn.v_proj.weight",
      "model.layers.4.mlp.down_proj.weight",
      "model.layers.4.mlp.gate_proj.weight",
      "model.layers.4.mlp.up_proj.weight",
      "model.layers.4.self_attn.k_proj.weight",
      "model.layers.4.self_attn.o_proj.weight",
      "model.layers.4.self_attn.q_proj.weight",
      "model.layers.4.self_attn.v_proj.weight",
      "model.layers.5.mlp.down_proj.weight",
      "model.layers.5.mlp.gate_proj.weight",
      "model.layers.5.mlp.up_proj.weight",
      "model.layers.5.self_attn.k_proj.weight",
      "model.layers.5.self_attn.o_proj.weight",
      "model.layers.5.self_attn.q_proj.weight",
      "model.layers.5.self_attn.v_proj.weight",
      "model.layers.6.mlp.down_proj.weight",
      "model.layers.6.mlp.gate_proj.weight",
      "model.layers.6.mlp.up_proj.weight",
      "model.layers.6.self_attn.k_proj.weight",
      "model.layers.6.self_attn.o_proj.weight",
      "model.layers.6.self_attn.q_proj.weight",
      "model.layers.6.self_attn.v_proj.weight",
      "model.layers.7.mlp.down_proj.weight",
      "model.layers.7.mlp.gate_proj.weight",
      "model.layers.7.mlp.up_proj.weight",
      "model.layers.7.self_attn.k_proj.weight",
      "model.layers.7.self_attn.o_proj.weight",
      "model.layers.7.self_attn.q_proj.weight",
      "model.layers.7.self_attn.v_proj.weight",
      "model.layers.8.mlp.down_proj.weight",
      "model.layers.8.mlp.gate_proj.weight",
      "model.layers.8.mlp.up_proj.weight",
      "model.layers.8.self_attn.k_proj.weight",
      "model.layers.8.self_attn.o_proj.weight",
      "model.layers.8.self_attn.q_proj.weight",
      "model.layers.8.self_attn.v_proj.weight",
      "model.layers.9.mlp.down_proj.weight",
      "model.layers.9.mlp.gate_proj.weight",
      "model.layers.9.mlp.up_proj.weight",
      "model.layers.9.self_attn.k_proj.weight",
      "model.layers.9.self_attn.o_proj.weight",
      "model.layers.9.self_attn.q_proj.weight",
      "model.layers.9.self_attn.v_proj.weight",
      "model.layers.10.mlp.down_proj.weight",
      "model.layers.10.mlp.gate_proj.weight",
      "model.layers.10.mlp.up_proj.weight",
      "model.layers.10.self_attn.k_proj.weight",
      "model.layers.10.self_attn.o_proj.weight",
      "model.layers.10.self_attn.q_proj.weight",
      "model.layers.10.self_attn.v_proj.weight",
      "model.layers.11.mlp.down_proj.weight",
      "model.layers.11.mlp.gate_proj.weight",
      "model.layers.11.mlp.up_proj.weight",
      "model.layers.11.self_attn.k_proj.weight",
      "model.layers.11.self_attn.o_proj.weight",
      "model.layers.11.self_attn.q_proj.weight",
      "model.layers.11.self_attn.v_proj.weight",
      "model.layers.12.mlp.down_proj.weight",
      "model.layers.12.mlp.gate_proj.weight",
      "model.layers.12.mlp.up_proj.weight",
      "model.layers.12.self_attn.k_proj.weight",
      "model.layers.12.self_attn.o_proj.weight",
      "model.layers.12.self_attn.q_proj.weight",
      "model.layers.12.self_attn.v_proj.weight",
      "model.layers.13.mlp.down_proj.weight",
      "model.layers.13.mlp.gate_proj.weight",
      "model.layers.13.mlp.up_proj.weight",
      "model.layers.13.self_attn.k_proj.weight",
      "model.layers.13.self_attn.o_proj.weight",
      "model.layers.13.self_attn.q_proj.weight",
      "model.layers.13.self_attn.v_proj.weight",
      "model.layers.14.mlp.down_proj.weight",
      "model.layers.14.mlp.gate_proj.weight",
      "model.layers.14.mlp.up_proj.weight",
      "model.layers.14.self_attn.k_proj.weight",
      "model.layers.14.self_attn.o_proj.weight",
      "model.layers.14.self_attn.q_proj.weight",
      "model.layers.14.self_attn.v_proj.weight",
      "model.layers.15.mlp.down_proj.weight",
      "model.layers.15.mlp.gate_proj.weight",
      "model.layers.15.mlp.up_proj.weight",
      "model.layers.15.self_attn.k_proj.weight",
      "model.layers.15.self_attn.o_proj.weight",
      "model.layers.15.self_attn.q_proj.weight",
      "model.layers.15.self_attn.v_proj.weight",
      "model.layers.16.mlp.down_proj.weight",
      "model.layers.16.mlp.gate_proj.weight",
      "model.layers.16.mlp.up_proj.weight",
      "model.layers.16.self_attn.k_proj.weight",
      "model.layers.16.self_attn.o_proj.weight",
      "model.layers.16.self_attn.q_proj.weight",
      "model.layers.16.self_attn.v_proj.weight",
      "model.layers.17.mlp.down_proj.weight",
      "model.layers.17.mlp.gate_proj.weight",
      "model.layers.17.mlp.up_proj.weight",
      "model.layers.17.self_attn.k_proj.weight",
      "model.layers.17.self_attn.o_proj.weight",
      "model.layers.17.self_attn.q_proj.weight",
      "model.layers.17.self_attn.v_proj.weight",
      "model.layers.18.mlp.down_proj.weight",
      "model.layers.18.mlp.gate_proj.weight",
      "model.layers.18.mlp.up_proj.weight",
      "model.layers.18.self_attn.k_proj.weight",
      "model.layers.18.self_attn.o_proj.weight",
      "model.layers.18.self_attn.q_proj.weight",
      "model.layers.18.self_attn.v_proj.weight",
      "model.layers.19.mlp.down_proj.weight",
      "model.layers.19.mlp.gate_proj.weight",
      "model.layers.19.mlp.up_proj.weight",
      "model.layers.19.self_attn.k_proj.weight",
      "model.layers.19.self_attn.o_proj.weight",
      "model.layers.19.self_attn.q_proj.weight",
      "model.layers.19.self_attn.v_proj.weight",
      "model.layers.20.mlp.down_proj.weight",
      "model.layers.20.mlp.gate_proj.weight",
      "model.layers.20.mlp.up_proj.weight",
      "model.layers.20.self_attn.k_proj.weight",
      "model.layers.20.self_attn.o_proj.weight",
      "model.layers.20.self_attn.q_proj.weight",
      "model.layers.20.self_attn.v_proj.weight",
      "model.layers.21.mlp.down_proj.weight",
      "model.layers.21.mlp.gate_proj.weight",
      "model.layers.21.mlp.up_proj.weight",
      "model.layers.21.self_attn.k_proj.weight",
      "model.layers.21.self_attn.o_proj.weight",
      "model.layers.21.self_attn.q_proj.weight",
      "model.layers.21.self_attn.v_proj.weight",
      "model.layers.22.mlp.down_proj.weight",
      "model.layers.22.mlp.gate_proj.weight",
      "model.layers.22.mlp.up_proj.weight",
      "model.layers.22.self_attn.k_proj.weight",
      "model.layers.22.self_attn.o_proj.weight",
      "model.layers.22.self_attn.q_proj.weight",
      "model.layers.22.self_attn.v_proj.weight",
      "model.layers.23.mlp.down_proj.weight",
      "model.layers.23.mlp.gate_proj.weight",
      "model.layers.23.mlp.up_proj.weight",
      "model.layers.23.self_attn.k_proj.weight",
      "model.layers.23.self_attn.o_proj.weight",
      "model.layers.23.self_attn.q_proj.weight",
      "model.layers.23.self_attn.v_proj.weight",
      "model.layers.24.mlp.down_proj.weight",
      "model.layers.24.mlp.gate_proj.weight",
      "model.layers.24.mlp.up_proj.weight",
      "model.layers.24.self_attn.k_proj.weight",
      "model.layers.24.self_attn.o_proj.weight",
      "model.layers.24.self_attn.q_proj.weight",
      "model.layers.24.self_attn.v_proj.weight",
      "model.layers.25.mlp.down_proj.weight",
      "model.layers.25.mlp.gate_proj.weight",
      "model.layers.25.mlp.up_proj.weight",
      "model.layers.25.self_attn.k_proj.weight",
      "model.layers.25.self_attn.o_proj.weight",
      "model.layers.25.self_attn.q_proj.weight",
      "model.layers.25.self_attn.v_proj.weight",
      "model.layers.26.mlp.down_proj.weight",
      "model.layers.26.mlp.gate_proj.weight",
      "model.layers.26.mlp.up_proj.weight",
      "model.layers.26.self_attn.k_proj.weight",
      "model.layers.26.self_attn.o_proj.weight",
      "model.layers.26.self_attn.q_proj.weight",
      "model.layers.26.self_attn.v_proj.weight",
      "model.layers.27.mlp.down_proj.weight",
      "model.layers.27.mlp.gate_proj.weight",
      "model.layers.27.mlp.up_proj.weight",
      "model.layers.27.self_attn.k_proj.weight",
      "model.layers.27.self_attn.o_proj.weight",
      "model.layers.27.self_attn.q_proj.weight",
      "model.layers.27.self_attn.v_proj.weight",
      "model.layers.28.mlp.down_proj.weight",
      "model.layers.28.mlp.gate_proj.weight",
      "model.layers.28.mlp.up_proj.weight",
      "model.layers.28.self_attn.k_proj.weight",
      "model.layers.28.self_attn.o_proj.weight",
      "model.layers.28.self_attn.q_proj.weight",
      "model.layers.28.self_attn.v_proj.weight",
      "model.layers.29.mlp.down_proj.weight",
      "model.layers.29.mlp.gate_proj.weight",
      "model.layers.29.mlp.up_proj.weight",
      "model.layers.29.self_attn.k_proj.weight",
      "model.layers.29.self_attn.o_proj.weight",
      "model.layers.29.self_attn.q_proj.weight",
      "model.layers.29.self_attn.v_proj.weight",
      "model.layers.30.mlp.down_proj.weight",
      "model.layers.30.mlp.gate_proj.weight",
      "model.layers.30.mlp.up_proj.weight",
      "model.layers.30.self_attn.k_proj.weight",
      "model.layers.30.self_attn.o_proj.weight",
      "model.layers.30.self_attn.q_proj.weight",
      "model.layers.30.self_attn.v_proj.weight",
      "model.layers.31.mlp.down_proj.weight",
      "model.layers.31.mlp.gate_proj.weight",
      "model.layers.31.mlp.up_proj.weight",
      "model.layers.31.self_attn.k_proj.weight",
      "model.layers.31.self_attn.o_proj.weight",
      "model.layers.31.self_attn.q_proj.weight",
      "model.layers.31.self_attn.v_proj.weight",
      "model.layers.32.mlp.down_proj.weight",
      "model.layers.32.mlp.gate_proj.weight",
      "model.layers.32.mlp.up_proj.weight",
      "model.layers.32.self_attn.k_proj.weight",
      "model.layers.32.self_attn.o_proj.weight",
      "model.layers.32.self_attn.q_proj.weight",
      "model.layers.32.self_attn.v_proj.weight",
      "model.layers.33.mlp.down_proj.weight",
      "model.layers.33.mlp.gate_proj.weight",
      "model.layers.33.mlp.up_proj.weight",
      "model.layers.33.self_attn.k_proj.weight",
      "model.layers.33.self_attn.o_proj.weight",
      "model.layers.33.self_attn.q_proj.weight",
      "model.layers.33.self_attn.v_proj.weight",
      "model.layers.34.mlp.down_proj.weight",
      "model.layers.34.mlp.gate_proj.weight",
      "model.layers.34.mlp.up_proj.weight",
      "model.layers.34.self_attn.k_proj.weight",
      "model.layers.34.self_attn.o_proj.weight",
      "model.layers.34.self_attn.q_proj.weight",
      "model.layers.34.self_attn.v_proj.weight",
      "model.layers.35.mlp.down_proj.weight",
      "model.layers.35.mlp.gate_proj.weight",
      "model.layers.35.mlp.up_proj.weight",
      "model.layers.35.self_attn.k_proj.weight",
      "model.layers.35.self_attn.o_proj.weight",
      "model.layers.35.self_attn.q_proj.weight",
      "model.layers.35.self_attn.v_proj.weight"
    ]
  },
  "modules_to_not_convert": [
    ".time_embed",
    ".emb_out",
    "patch_embed",
    ".x_embedder",
    "lm_head",
    ".final_layer",
    "lm_head.weight",
    ".img_out",
    ".emb_in",
    ".vid_out",
    "patch_emb",
    "patch_embedding",
    ".t_embedder",
    ".condition_embedder",
    "multi_modal_projector",
    "model.embed_tokens",
    "wte",
    ".txt_in",
    ".proj_out",
    ".img_in",
    "model.embed_tokens.weight",
    ".vid_in",
    "time_text_embed",
    ".context_embedder",
    ".y_embedder",
    ".norm_out",
    ".txt_out"
  ],
  "non_blocking": false,
  "quant_conv": false,
  "quant_method": "sdnq",
  "quantization_device": null,
  "quantized_matmul_dtype": null,
  "return_device": null,
  "sdnq_version": "0.1.4",
  "svd_rank": 32,
  "svd_steps": 32,
  "use_dynamic_quantization": true,
  "use_grad_ckpt": true,
  "use_quantized_matmul": false,
  "use_quantized_matmul_conv": false,
  "use_static_quantization": true,
  "use_stochastic_rounding": false,
  "use_svd": false,
  "weights_dtype": "uint4"
}