pe/quantization_config.json

{
  "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",
    "lm_head.weight",
    "wte",
    "model.embed_tokens",
    "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",
    "model.embed_tokens.weight",
    "lm_head.weight",
    "model.embed_tokens.weight",
    "model.layers.0.input_layernorm.weight",
    "model.layers.0.post_attention_layernorm.weight",
    "model.layers.1.input_layernorm.weight",
    "model.layers.1.post_attention_layernorm.weight",
    "model.layers.2.input_layernorm.weight",
    "model.layers.2.post_attention_layernorm.weight",
    "model.layers.3.input_layernorm.weight",
    "model.layers.3.post_attention_layernorm.weight",
    "model.layers.4.input_layernorm.weight",
    "model.layers.4.post_attention_layernorm.weight",
    "model.layers.5.input_layernorm.weight",
    "model.layers.5.post_attention_layernorm.weight",
    "model.layers.6.input_layernorm.weight",
    "model.layers.6.post_attention_layernorm.weight",
    "model.layers.7.input_layernorm.weight",
    "model.layers.7.post_attention_layernorm.weight",
    "model.layers.8.input_layernorm.weight",
    "model.layers.8.post_attention_layernorm.weight",
    "model.layers.9.input_layernorm.weight",
    "model.layers.9.post_attention_layernorm.weight",
    "model.layers.10.input_layernorm.weight",
    "model.layers.10.post_attention_layernorm.weight",
    "model.layers.11.input_layernorm.weight",
    "model.layers.11.post_attention_layernorm.weight",
    "model.layers.12.input_layernorm.weight",
    "model.layers.12.post_attention_layernorm.weight",
    "model.layers.13.input_layernorm.weight",
    "model.layers.13.post_attention_layernorm.weight",
    "model.layers.14.input_layernorm.weight",
    "model.layers.14.post_attention_layernorm.weight",
    "model.layers.15.input_layernorm.weight",
    "model.layers.15.post_attention_layernorm.weight",
    "model.layers.16.input_layernorm.weight",
    "model.layers.16.post_attention_layernorm.weight",
    "model.layers.17.input_layernorm.weight",
    "model.layers.17.post_attention_layernorm.weight",
    "model.layers.18.input_layernorm.weight",
    "model.layers.18.post_attention_layernorm.weight",
    "model.layers.19.input_layernorm.weight",
    "model.layers.19.post_attention_layernorm.weight",
    "model.layers.20.input_layernorm.weight",
    "model.layers.20.post_attention_layernorm.weight",
    "model.layers.21.input_layernorm.weight",
    "model.layers.21.post_attention_layernorm.weight",
    "model.layers.22.input_layernorm.weight",
    "model.layers.22.post_attention_layernorm.weight",
    "model.layers.23.input_layernorm.weight",
    "model.layers.23.post_attention_layernorm.weight",
    "model.layers.24.input_layernorm.weight",
    "model.layers.24.post_attention_layernorm.weight",
    "model.layers.25.input_layernorm.weight",
    "model.layers.25.post_attention_layernorm.weight",
    "model.norm.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"
}