Struct ModelConfig 

pub struct ModelConfig {
    pub model_type: ModelType,
    pub variant: ModelVariant,
    pub model_path: PathBuf,
    pub thread_pool_size: usize,
    pub optimization_level: u8,
}

Configuration for loading a model

Fields

model_type: ModelType

Type of model

variant: ModelVariant

Model variant (precision)

model_path: PathBuf

Path to ONNX model file

thread_pool_size: usize

Number of threads for inference

optimization_level: u8

ONNX graph optimization level (0-3)

Implementations

impl ModelConfig

pub fn new( model_type: ModelType, variant: ModelVariant, model_path: PathBuf, ) -> Self

Create a new model configuration

Arguments

• model_type - Type of model (PromptInjection, Toxicity, Sentiment)
• variant - Model variant (FP32, FP16, INT8)
• model_path - Path to ONNX model file

Example

use llm_shield_models::{ModelConfig, ModelType, ModelVariant};
use std::path::PathBuf;

let config = ModelConfig::new(
    ModelType::PromptInjection,
    ModelVariant::FP16,
    PathBuf::from("/path/to/model.onnx")
);

pub fn with_thread_pool_size(self, size: usize) -> Self

Set the thread pool size

pub fn with_optimization_level(self, level: u8) -> Self

Set the optimization level (0-3)

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.