EngramHashTables

spark_model::layers::engram_v41

Struct EngramHashTables

pub struct EngramHashTables {
    pub layer_ids: Vec<usize>,
    pub max_ngram: usize,
    pub n_heads: usize,
    pub pad_id: i64,
    pub token_map: Vec<i64>,
    pub multipliers: Vec<Vec<i64>>,
    pub primes: Vec<Vec<Vec<i64>>>,
    pub offsets: Vec<Vec<i64>>,
}

Expand description

The hash tables, shaped as the reference indexes them.

Fields§

§layer_ids: Vec<usize>§max_ngram: usize§n_heads: usize§pad_id: i64

token_map[engram_pad_token_id]: the pad in the compressed space.

§token_map: Vec<i64>

[vocab], -1 = unmapped.

§multipliers: Vec<Vec<i64>>

[layer][lookback]

§primes: Vec<Vec<Vec<i64>>>

[layer][ngram_size - 2][head]

§offsets: Vec<Vec<i64>>

[layer][(ngram_size - 2) * n_heads + head]

Implementations§

impl EngramHashTables

pub fn from_flat( layer_ids: Vec<usize>, max_ngram: usize, n_heads: usize, pad_token_id: u32, token_map: Vec<i64>, multipliers: &[u64], primes: &[u64], offsets: &[u64], ) -> Result<Self>

From the flat GGUF metadata arrays (deepseek41.engram.*, as ModelConfig carries them): multipliers [layers * max_ngram], primes [layers * (max_ngram - 1) * n_heads], offsets the same length.

pub fn n_hash_cols(&self) -> usize

pub fn n_layers(&self) -> usize

pub fn hash_index(&self, layer: usize) -> Option<usize>

Position of model layer layer in layer_ids.

Auto Trait Implementations§

impl Freeze for EngramHashTables

impl RefUnwindSafe for EngramHashTables

impl Send for EngramHashTables

impl Sync for EngramHashTables

impl Unpin for EngramHashTables

impl UnwindSafe for EngramHashTables

Blanket Implementations§

impl<T> Any for T
where T: 'static + ?Sized,

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

impl<T> Borrow<T> for T
where T: ?Sized,

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

impl<T> BorrowMut<T> for T
where T: ?Sized,

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more

impl<T> From<T> for T

fn from(t: T) -> T

Returns the argument unchanged.

impl<T> Instrument for T

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided [Span], returning an Instrumented wrapper. Read more

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more

impl<T, U> Into<U> for T
where U: From<T>,

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

impl<T, U> TryFrom<U> for T
where U: Into<T>,

type Error = Infallible

The type returned in the event of a conversion error.

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

fn vzip(self) -> V

impl<T> WithSubscriber for T

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a [WithDispatch] wrapper. Read more

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a [WithDispatch] wrapper. Read more

impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
where ST: ?Sized, DT: ?Sized,

impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
where ST: ?Sized, DT: ?Sized,

impl<T> Read<Exclusive, BecauseExclusive> for T
where T: ?Sized,