Struct ModelConfig 

pub struct ModelConfig {
    pub architectures: Vec<String>,
    pub hidden_size: usize,
    pub num_attention_heads: usize,
    pub num_key_value_heads: Option<usize>,
    pub num_hidden_layers: usize,
    pub intermediate_size: usize,
    pub vocab_size: usize,
    pub max_position_embeddings: usize,
    pub rms_norm_eps: f32,
    pub rope_theta: f32,
    pub tie_word_embeddings: bool,
    pub model_type: String,
}

Model configuration from config.json

Fields

architectures: Vec<String>

Model architecture type

hidden_size: usize

Hidden size / embedding dimension

num_attention_heads: usize

Number of attention heads

num_key_value_heads: Option<usize>

Number of key-value heads (for GQA)

num_hidden_layers: usize

Number of transformer layers

intermediate_size: usize

Intermediate size (MLP)

vocab_size: usize

Vocabulary size

max_position_embeddings: usize

Maximum context length

rms_norm_eps: f32

RMS norm epsilon

rope_theta: f32

RoPE theta

tie_word_embeddings: bool

Tie word embeddings

model_type: String

Model type string

Implementations

impl ModelConfig

pub fn from_file(path: &Path) -> HubResult<Self>

Load config from a config.json file.

pub fn from_model_dir(model_dir: &Path) -> HubResult<Self>

Load config from a model directory.

pub fn head_dim(&self) -> usize

Get the head dimension.

pub fn kv_heads(&self) -> usize

Get number of KV heads (for GQA).

pub fn uses_gqa(&self) -> bool

Check if using Grouped Query Attention.

Trait Implementations

impl Clone for ModelConfig

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 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.