Struct TransformerConfig 

pub struct TransformerConfig {
    pub hidden_size: usize,
    pub num_attention_heads: usize,
    pub num_kv_heads: usize,
    pub intermediate_size: usize,
    pub num_hidden_layers: usize,
    pub vocab_size: usize,
    pub max_position_embeddings: usize,
    pub rms_norm_eps: f32,
    pub rope_theta: f32,
    pub use_bias: bool,
}

Configuration for transformer models

Fields

hidden_size: usize

Hidden dimension (embedding size)

num_attention_heads: usize

Number of attention heads

num_kv_heads: usize

Number of key-value heads (for grouped-query attention)

intermediate_size: usize

Feed-forward network intermediate dimension

num_hidden_layers: usize

Number of transformer layers

vocab_size: usize

Vocabulary size

max_position_embeddings: usize

Maximum sequence length

rms_norm_eps: f32

RMS normalization epsilon

rope_theta: f32

RoPE theta base

use_bias: bool

Whether to use bias in linear layers

Implementations

impl TransformerConfig

pub fn llama2_7b() -> Self

LLaMA 2 7B configuration

pub fn llama2_13b() -> Self

LLaMA 2 13B configuration

pub fn mistral_7b() -> Self

Mistral 7B configuration

pub fn qwen2_0_5b() -> Self

Qwen2 0.5B configuration (good for testing)

pub fn tiny() -> Self

Tiny configuration for testing

pub fn head_dim(&self) -> usize

Per-head dimension

Trait Implementations

impl Clone for TransformerConfig

fn clone(&self) -> TransformerConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TransformerConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for TransformerConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for TransformerConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.