text_encoder/quantization_config.json

{
  "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": [
    "layers.0.self_attn.q_norm.weight",
    "layers.0.self_attn.k_norm.weight",
    "layers.0.input_layernorm.weight",
    "layers.0.post_attention_layernorm.weight",
    "layers.1.self_attn.q_norm.weight",
    "layers.1.self_attn.k_norm.weight",
    "layers.1.input_layernorm.weight",
    "layers.1.post_attention_layernorm.weight",
    "layers.2.self_attn.q_norm.weight",
    "layers.2.self_attn.k_norm.weight",
    "layers.2.input_layernorm.weight",
    "layers.2.post_attention_layernorm.weight",
    "layers.3.self_attn.q_norm.weight",
    "layers.3.self_attn.k_norm.weight",
    "layers.3.input_layernorm.weight",
    "layers.3.post_attention_layernorm.weight",
    "layers.4.self_attn.q_norm.weight",
    "layers.4.self_attn.k_norm.weight",
    "layers.4.input_layernorm.weight",
    "layers.4.post_attention_layernorm.weight",
    "layers.5.self_attn.q_norm.weight",
    "layers.5.self_attn.k_norm.weight",
    "layers.5.input_layernorm.weight",
    "layers.5.post_attention_layernorm.weight",
    "layers.6.self_attn.q_norm.weight",
    "layers.6.self_attn.k_norm.weight",
    "layers.6.input_layernorm.weight",
    "layers.6.post_attention_layernorm.weight",
    "layers.7.self_attn.q_norm.weight",
    "layers.7.self_attn.k_norm.weight",
    "layers.7.input_layernorm.weight",
    "layers.7.post_attention_layernorm.weight",
    "layers.8.self_attn.q_norm.weight",
    "layers.8.self_attn.k_norm.weight",
    "layers.8.input_layernorm.weight",
    "layers.8.post_attention_layernorm.weight",
    "layers.9.self_attn.q_norm.weight",
    "layers.9.self_attn.k_norm.weight",
    "layers.9.input_layernorm.weight",
    "layers.9.post_attention_layernorm.weight",
    "layers.10.self_attn.q_norm.weight",
    "layers.10.self_attn.k_norm.weight",
    "layers.10.input_layernorm.weight",
    "layers.10.post_attention_layernorm.weight",
    "layers.11.self_attn.q_norm.weight",
    "layers.11.self_attn.k_norm.weight",
    "layers.11.input_layernorm.weight",
    "layers.11.post_attention_layernorm.weight",
    "layers.12.self_attn.q_norm.weight",
    "layers.12.self_attn.k_norm.weight",
    "layers.12.input_layernorm.weight",
    "layers.12.post_attention_layernorm.weight",
    "layers.13.self_attn.q_norm.weight",
    "layers.13.self_attn.k_norm.weight",
    "layers.13.input_layernorm.weight",
    "layers.13.post_attention_layernorm.weight",
    "layers.14.self_attn.q_norm.weight",
    "layers.14.self_attn.k_norm.weight",
    "layers.14.input_layernorm.weight",
    "layers.14.post_attention_layernorm.weight",
    "layers.15.self_attn.q_norm.weight",
    "layers.15.self_attn.k_norm.weight",
    "layers.15.input_layernorm.weight",
    "layers.15.post_attention_layernorm.weight",
    "layers.16.self_attn.q_norm.weight",
    "layers.16.self_attn.k_norm.weight",
    "layers.16.input_layernorm.weight",
    "layers.16.post_attention_layernorm.weight",
    "layers.17.self_attn.q_norm.weight",
    "layers.17.self_attn.k_norm.weight",
    "layers.17.input_layernorm.weight",
    "layers.17.post_attention_layernorm.weight",
    "layers.18.self_attn.q_norm.weight",
    "layers.18.self_attn.k_norm.weight",
    "layers.18.input_layernorm.weight",
    "layers.18.post_attention_layernorm.weight",
    "layers.19.self_attn.q_norm.weight",
    "layers.19.self_attn.k_norm.weight",
    "layers.19.input_layernorm.weight",
    "layers.19.post_attention_layernorm.weight",
    "layers.20.self_attn.q_norm.weight",
    "layers.20.self_attn.k_norm.weight",
    "layers.20.input_layernorm.weight",
    "layers.20.post_attention_layernorm.weight",
    "layers.21.self_attn.q_norm.weight",
    "layers.21.self_attn.k_norm.weight",
    "layers.21.input_layernorm.weight",
    "layers.21.post_attention_layernorm.weight",
    "layers.22.self_attn.q_norm.weight",
    "layers.22.self_attn.k_norm.weight",
    "layers.22.input_layernorm.weight",
    "layers.22.post_attention_layernorm.weight",
    "layers.23.self_attn.q_norm.weight",
    "layers.23.self_attn.k_norm.weight",
    "layers.23.input_layernorm.weight",
    "layers.23.post_attention_layernorm.weight",
    "layers.24.self_attn.q_norm.weight",
    "layers.24.self_attn.k_norm.weight",
    "layers.24.input_layernorm.weight",
    "layers.24.post_attention_layernorm.weight",
    "layers.25.self_attn.q_norm.weight",
    "layers.25.self_attn.k_norm.weight",
    "layers.25.input_layernorm.weight",
    "layers.25.post_attention_layernorm.weight",
    "layers.26.self_attn.q_norm.weight",
    "layers.26.self_attn.k_norm.weight",
    "layers.26.input_layernorm.weight",
    "layers.26.post_attention_layernorm.weight",
    "layers.27.self_attn.q_norm.weight",
    "layers.27.self_attn.k_norm.weight",
    "layers.27.input_layernorm.weight",
    "layers.27.post_attention_layernorm.weight",
    "layers.28.self_attn.q_norm.weight",
    "layers.28.self_attn.k_norm.weight",
    "layers.28.input_layernorm.weight",
    "layers.28.post_attention_layernorm.weight",
    "layers.29.self_attn.q_norm.weight",
    "layers.29.self_attn.k_norm.weight",
    "layers.29.input_layernorm.weight",
    "layers.29.post_attention_layernorm.weight",
    "layers.30.self_attn.q_norm.weight",
    "layers.30.self_attn.k_norm.weight",
    "layers.30.input_layernorm.weight",
    "layers.30.post_attention_layernorm.weight",
    "layers.31.self_attn.q_norm.weight",
    "layers.31.self_attn.k_norm.weight",
    "layers.31.input_layernorm.weight",
    "layers.31.post_attention_layernorm.weight",
    "layers.32.self_attn.q_norm.weight",
    "layers.32.self_attn.k_norm.weight",
    "layers.32.input_layernorm.weight",
    "layers.32.post_attention_layernorm.weight",
    "layers.33.self_attn.q_norm.weight",
    "layers.33.self_attn.k_norm.weight",
    "layers.33.input_layernorm.weight",
    "layers.33.post_attention_layernorm.weight",
    "layers.34.self_attn.q_norm.weight",
    "layers.34.self_attn.k_norm.weight",
    "layers.34.input_layernorm.weight",
    "layers.34.post_attention_layernorm.weight",
    "layers.35.self_attn.q_norm.weight",
    "layers.35.self_attn.k_norm.weight",
    "layers.35.input_layernorm.weight",
    "layers.35.post_attention_layernorm.weight",
    "norm.weight"
  ],
  "modules_to_not_use_matmul": [],
  "non_blocking": false,
  "quant_conv": false,
  "quant_embedding": true,
  "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_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"
}