Struct ExpertAppend 

pub struct ExpertAppend {
    pub count: usize,
    pub shell_quantile: f32,
    pub rank: usize,
}

Parameters of a kind = "expert_append" record (SkillRecord.experts): count new experts in EACH of SkillRecord.layers (the grown MoE layers, any non-empty subset), appended after the experts already present in that layer. The per-layer index of the new experts is not stored — the reader computes it (expert_append_base).

Fields

count: usize

New experts per grown layer (≥ 1).

shell_quantile: f32

The quantile (in [0, 1]) of the reconstruction errors of the tokens each expert won on the growth corpus that the trainer wrote into its desc.shell — provenance of the shell, not used by the reader.

rank: usize

Rank of every new expert’s desc.u — must equal the trunk’s expert 0 rank in every grown layer (trunk_expert_rank); 0 when the trunk carries no desc.u (then the record carries none either).

Trait Implementations

impl Clone for ExpertAppend

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ExpertAppend

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ExpertAppend

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ExpertAppend

fn eq(&self, other: &Self) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl Serialize for ExpertAppend

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ExpertAppend