Type Alias: GgufMetadataDefaultArchitectureType

type GgufMetadataDefaultArchitectureType: {
  vocab_size: number;
  context_length: number;
  embedding_length: number;
  block_count: number;
  feed_forward_length: number;
  use_parallel_residual: boolean;
  tensor_data_layout: string;
  expert_count: number;
  expert_used_count: number;
  pooling_type: GgufMetadataArchitecturePoolingType;
  logit_scale: number;
  attention: {
     head_count: number;
     head_count_kv: number;
     max_alibi_bias: number;
     clamp_kqv: number;
     layer_norm_epsilon: number;
     layer_norm_rms_epsilon: number;
     key_length: number;
     value_length: number;
     causal: boolean;
    };
  rope: {
     dimension_count: number;
     freq_base: number;
     scale_linear: number;
     scaling: {
        type: "none" | "linear" | "yarn" | string;
        factor: number;
        original_context_length: number;
        finetuned: boolean;
       };
    };
  ssm: {
     conv_kernel: number;
     inner_size: number;
     state_size: number;
     time_step_rank: number;
    };
};

Type declaration

vocab_size?

readonly optional vocab_size: number;

context_length?

readonly optional context_length: number;

embedding_length?

readonly optional embedding_length: number;

block_count?

readonly optional block_count: number;

feed_forward_length?

readonly optional feed_forward_length: number;

use_parallel_residual?

readonly optional use_parallel_residual: boolean;

tensor_data_layout?

readonly optional tensor_data_layout: string;

expert_count?

readonly optional expert_count: number;

expert_used_count?

readonly optional expert_used_count: number;

pooling_type?

readonly optional pooling_type: GgufMetadataArchitecturePoolingType;

logit_scale?

readonly optional logit_scale: number;

attention?

readonly optional attention: {
  head_count: number;
  head_count_kv: number;
  max_alibi_bias: number;
  clamp_kqv: number;
  layer_norm_epsilon: number;
  layer_norm_rms_epsilon: number;
  key_length: number;
  value_length: number;
  causal: boolean;
};

attention.head_count?

readonly optional head_count: number;

attention.head_count_kv?

readonly optional head_count_kv: number;

attention.max_alibi_bias?

readonly optional max_alibi_bias: number;

attention.clamp_kqv?

readonly optional clamp_kqv: number;

attention.layer_norm_epsilon?

readonly optional layer_norm_epsilon: number;

attention.layer_norm_rms_epsilon?

readonly optional layer_norm_rms_epsilon: number;

attention.key_length?

readonly optional key_length: number;

attention.value_length?

readonly optional value_length: number;

attention.causal?

readonly optional causal: boolean;

rope?

readonly optional rope: {
  dimension_count: number;
  freq_base: number;
  scale_linear: number;
  scaling: {
     type: "none" | "linear" | "yarn" | string;
     factor: number;
     original_context_length: number;
     finetuned: boolean;
    };
};

rope.dimension_count?

readonly optional dimension_count: number;

rope.freq_base?

readonly optional freq_base: number;

rope.scale_linear?

readonly optional scale_linear: number;

rope.scaling?

readonly optional scaling: {
  type: "none" | "linear" | "yarn" | string;
  factor: number;
  original_context_length: number;
  finetuned: boolean;
};

rope.scaling.type?

readonly optional type: "none" | "linear" | "yarn" | string;

rope.scaling.factor?

readonly optional factor: number;

rope.scaling.original_context_length?

readonly optional original_context_length: number;

rope.scaling.finetuned?

readonly optional finetuned: boolean;

ssm?

readonly optional ssm: {
  conv_kernel: number;
  inner_size: number;
  state_size: number;
  time_step_rank: number;
};

ssm.conv_kernel?

readonly optional conv_kernel: number;

ssm.inner_size?

readonly optional inner_size: number;

ssm.state_size?

readonly optional state_size: number;

ssm.time_step_rank?

readonly optional time_step_rank: number;

Defined in

gguf/types/GgufMetadataTypes.ts:259