Skip to main content

LlamaConfig

Struct LlamaConfig 

Source
pub struct LlamaConfig {
Show 20 fields pub version: u8, pub num_attention_heads: u32, pub num_key_value_heads: u32, pub hidden_size: u32, pub head_dim: u32, pub intermediate_size: u32, pub max_position_embeddings: u32, pub rms_norm_eps: f32, pub vocab_size: u32, pub original_vocab_size: u32, pub num_hidden_layers: u32, pub rope_theta: f32, pub rope_scaling: Option<RopeScaling>, pub hidden_activation: String, pub query_pre_attn_scalar: Option<f32>, pub use_qk_norm: bool, pub scale_embeddings: bool, pub layer_types: Vec<String>, pub rope_local_base_freq: Option<f32>, pub model_architecture: ModelArchitecture,
}
Expand description

Llama model configuration

Fields§

§version: u8

Llama version (1, 2, or 3)

§num_attention_heads: u32

Number of attention heads for queries

§num_key_value_heads: u32

Number of key-value heads (for GQA in Llama 2/3)

§hidden_size: u32

Hidden dimension size

§head_dim: u32

Head dimension

§intermediate_size: u32

Intermediate size for FFN

§max_position_embeddings: u32

Maximum position embeddings

§rms_norm_eps: f32

RMSNorm epsilon

§vocab_size: u32

Vocabulary size (may be padded)

§original_vocab_size: u32

Original vocabulary size (before padding)

§num_hidden_layers: u32

Number of hidden layers

§rope_theta: f32

RoPE theta

§rope_scaling: Option<RopeScaling>

RoPE scaling (for Llama 3)

§hidden_activation: String

Hidden activation function (silu for Llama, gelu_pytorch_tanh for Gemma3)

§query_pre_attn_scalar: Option<f32>

Query pre-attention scalar for QK-norm (Gemma3)

§use_qk_norm: bool

Use QK-norm (Gemma3)

§scale_embeddings: bool

Scale embeddings by sqrt(hidden_size) (Gemma3)

§layer_types: Vec<String>

Layer types for sliding window attention (Gemma3)

§rope_local_base_freq: Option<f32>

RoPE theta for local attention layers (Gemma3)

§model_architecture: ModelArchitecture

The real model architecture this LlamaModel stands in for.

LlamaModel is reused as the runtime for several architecturally-llama families (Llama, Qwen, Mistral). The tokenizer-config dispatch keys on ModelOperations::architecture(), so a Qwen3 checkpoint loaded via create_qwen_model must report Qwen here — otherwise the QwenTokenizerConfig (which pads the tokenizer vocab up to the model’s embedding size) is never applied and the tokenizer/embedding vocab mismatch silently causes a CUDA index-out-of-bounds on the embedding lookup (#143). Defaults to Llama; create_qwen_model overrides it.

Implementations§

Source§

impl LlamaConfig

Source

pub fn llama3_8b() -> LlamaConfig

Create config for Llama 3 8B

Source

pub fn llama3_70b() -> LlamaConfig

Create config for Llama 3 70B

Trait Implementations§

Source§

impl ArchitectureConfig for LlamaConfig

Source§

fn num_attention_heads(&self) -> usize

Number of attention heads for queries
Source§

fn num_key_value_heads(&self) -> usize

Number of key-value heads (for MQA/GQA)
Source§

fn hidden_size(&self) -> usize

Hidden dimension size
Source§

fn intermediate_size(&self) -> usize

Intermediate/FFN dimension size
Source§

fn head_dim(&self) -> usize

Head dimension (hidden_size / num_attention_heads)
Source§

fn vocab_size(&self) -> usize

Vocabulary size
Source§

fn max_position_embeddings(&self) -> usize

Maximum position embeddings
Source§

fn rope_theta(&self) -> Option<f32>

RoPE base frequency (if applicable)
Source§

fn rope_dim(&self) -> Option<usize>

RoPE dimension count (if different from head_dim)
Source§

fn layer_norm_eps(&self) -> f32

Layer normalization epsilon
Source§

fn use_rms_norm(&self) -> bool

Whether to use RMSNorm instead of LayerNorm
Source§

fn use_parallel_residual(&self) -> bool

Whether this architecture uses parallel attention and FFN
Source§

fn attention_type(&self) -> AttentionType

Get attention type (MHA, MQA, GQA)
Source§

fn default_dtype(&self) -> Kind

Default dtype for this architecture
Source§

impl Clone for LlamaConfig

Source§

fn clone(&self) -> LlamaConfig

Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§

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

Performs copy-assignment from source. Read more
Source§

impl Debug for LlamaConfig

Source§

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

Formats the value using the given formatter. Read more
Source§

impl Default for LlamaConfig

Source§

fn default() -> LlamaConfig

Returns the “default value” for a type. Read more

Auto Trait Implementations§

Blanket Implementations§

Source§

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

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
§

impl<T> Any for T
where T: Any,

§

fn into_any(self: Box<T>) -> Box<dyn Any>

§

fn into_any_rc(self: Rc<T>) -> Rc<dyn Any>

§

fn type_name(&self) -> &'static str

§

impl<T> AnySync for T
where T: Any + Send + Sync,

§

fn into_any_arc(self: Arc<T>) -> Arc<dyn Any + Sync + Send> ⓘ

§

impl<'a, T, E> AsTaggedExplicit<'a, E> for T
where T: 'a,

§

fn explicit(self, class: Class, tag: u32) -> TaggedParser<'a, Explicit, Self, E>

§

impl<'a, T, E> AsTaggedImplicit<'a, E> for T
where T: 'a,

§

fn implicit( self, class: Class, constructed: bool, tag: u32, ) -> TaggedParser<'a, Implicit, Self, E>

Source§

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

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

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

Source§

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

Mutably borrows from an owned value. Read more
Source§

impl<T> CloneToUninit for T
where T: Clone,

Source§

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)
Performs copy-assignment from self to dest. Read more
Source§

impl<T> DynClone for T
where T: Clone,

Source§

fn __clone_box(&self, _: Private) -> *mut ()

Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

§

impl<T> FromRef<T> for T
where T: Clone,

§

fn from_ref(input: &T) -> T

Converts to this type from a reference to the input type.
§

impl<T> FutureExt for T

§

fn with_context(self, otel_cx: Context) -> WithContext<Self>

Attaches the provided Context to this type, returning a WithContext wrapper. Read more
§

fn with_current_context(self) -> WithContext<Self>

Attaches the current Context to this type, returning a WithContext wrapper. Read more
§

impl<T, W> HasTypeWitness<W> for T
where W: MakeTypeWitness<Arg = T>, T: ?Sized,

§

const WITNESS: W = W::MAKE

A constant of the type witness
§

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

§

const TYPE_EQ: TypeEq<T, <T as Identity>::Type> = TypeEq::NEW

Proof that Self is the same type as Self::Type, provides methods for casting between Self and Self::Type.
§

type Type = T

The same type as Self, used to emulate type equality bounds (T == U) with associated type equality constraints (T: Identity<Type = U>).
§

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
Source§

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

Source§

fn into(self) -> U

Calls U::from(self).

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

Source§

impl<T> IntoEither for T

Source§

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

impl<T> IntoRequest<T> for T

Source§

fn into_request(self) -> Request<T>

Wrap the input message T in a tonic::Request
§

impl<T> JaggedSlice<T> for T

§

type Index = Index2

§

fn push_into(self, array: &mut Jagged<T>)

§

fn insert_into(self, index: <T as JaggedSlice<T>>::Index, array: &mut Jagged<T>)

§

impl<T> NoneValue for T
where T: Default,

§

type NoneType = T

§

fn null_value() -> T

The none-equivalent value.
§

impl<T> NoneValue for T
where T: Default,

§

type NoneType = T

§

fn null_value() -> T

The none-equivalent value.
§

impl<T> Pointable for T

§

const ALIGN: usize

The alignment of pointer.
§

type Init = T

The type for initializers.
§

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more
§

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more
§

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more
§

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more
§

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

§

fn and<P, B, E>(self, other: P) -> And<T, P>
where T: Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns [Action::Follow] only if self and other return Action::Follow. Read more
§

fn or<P, B, E>(self, other: P) -> Or<T, P>
where T: Policy<B, E>, P: Policy<B, E>,

Create a new Policy that returns [Action::Follow] if either self or other returns Action::Follow. Read more
Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
§

impl<T> ServiceExt for T

§

fn map_response_body<F>(self, f: F) -> MapResponseBody<Self, F>
where Self: Sized,

Apply a transformation to the response body. Read more
§

fn trace_for_http(self) -> Trace<Self, SharedClassifier<ServerErrorsAsFailures>>
where Self: Sized,

High level tracing that classifies responses using HTTP status codes. Read more
§

fn trace_for_grpc(self) -> Trace<Self, SharedClassifier<GrpcErrorsAsFailures>>
where Self: Sized,

High level tracing that classifies responses using gRPC headers. Read more
§

fn follow_redirects(self) -> FollowRedirect<Self>
where Self: Sized,

Follow redirect resposes using the Standard policy. Read more
Source§

impl<T> ToOwned for T
where T: Clone,

Source§

type Owned = T

The resulting type after obtaining ownership.
Source§

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more
Source§

fn clone_into(&self, target: &mut T)

Uses borrowed data to replace owned data, usually by cloning. Read more
Source§

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

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

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

Performs the conversion.
Source§

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

Source§

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

The type returned in the event of a conversion error.
Source§

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<T> ErasedDestructor for T
where T: 'static,

§

impl<T> MaybeSend for T
where T: Send,

§

impl<T> MaybeSend for T
where T: Send,

§

impl<T> MaybeSync for T
where T: Sync,

§

impl<T> MaybeSync for T
where T: Sync,

§

impl<E> ResultError for E
where E: Send + Debug + Sync,

§

impl<T> ResultType for T
where T: Send + Clone + Sync + Debug,

§

impl<T> SendSyncUnwindSafe for T
where T: Send + Sync + UnwindSafe + ?Sized,

Source§

impl<T> TerminalState for T
where T: Clone + Send + Sync,