Struct ModelConfig 

pub struct ModelConfig {

    pub vocab_size: usize,
    pub hidden_size: usize,
    pub num_layers: usize,
    pub num_attention_heads: usize,
    pub num_key_value_heads: Option<usize>,
    pub intermediate_size: usize,
    pub max_position_embeddings: usize,
    pub rms_norm_eps: f32,
    pub rope_theta: Option<f32>,
    pub use_sliding_window: Option<bool>,
    pub sliding_window: Option<usize>,
    pub model_type: Option<String>,
    pub architectures: Option<Vec<String>>,
}

Model configuration structure

Fields

vocab_size: usize

Vocabulary size

hidden_size: usize

Hidden layer dimension

num_layers: usize

Number of Transformer layers

num_attention_heads: usize

Number of attention heads

num_key_value_heads: Option<usize>

Number of key-value heads (for GQA)

intermediate_size: usize

Feedforward network intermediate layer dimension

max_position_embeddings: usize

Maximum position embedding length

rms_norm_eps: f32

RMS normalization epsilon value

rope_theta: Option<f32>

RoPE theta parameter

use_sliding_window: Option<bool>

Whether to use sliding window attention

sliding_window: Option<usize>

Sliding window size

model_type: Option<String>

Model type

architectures: Option<Vec<String>>

Architecture names

Trait Implementations

impl Clone for ModelConfig

fn clone(&self) -> ModelConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelConfig

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

Formats the value using the given formatter.

impl Default for ModelConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ModelConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ModelConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.