Struct CLIPModelV2 

pub struct CLIPModelV2 { /* private fields */ }

Main CLIP model implementation

Implementations

impl CLIPModelV2

pub fn encode_text(&self, input_ids: &Tensor) -> Result<Tensor>

Encode text into normalized embeddings

pub fn encode_image(&self, pixel_values: &Tensor) -> Result<Tensor>

Encode image into normalized embeddings

pub fn compute_similarity( &self, text_features: &Tensor, image_features: &Tensor, ) -> Result<Tensor>

Compute similarity between text and image embeddings

Trait Implementations

impl Model for CLIPModelV2

type Config = CLIPConfig

Model configuration type

fn new(config: CLIPConfig) -> Result<Self>

Create new model instance

fn from_weights(config: CLIPConfig, weights: ModelWeights) -> Result<Self>

Load model with weights

fn forward(&self, inputs: &ModelInputs) -> Result<ModelOutputs>

Forward pass - core inference method

fn generate(&self, _prompt: &str, _config: &GenerationConfig) -> Result<String>

Generate text (high-level interface)

fn config(&self) -> &Self::Config

Get model configuration

fn memory_requirements(&self) -> MemoryRequirements

Get model memory requirements

fn to_device(&mut self, device: &Device) -> Result<()>

Move model to device