Struct Lfm2Conv 

pub struct Lfm2Conv {
    pub in_proj: Linear,
    pub conv_weight: Tensor,
    pub conv_bias: Tensor,
    pub out_proj: Linear,
}

LFM2 short-convolution operator: projection, depthwise conv, projection.

Fields

in_proj: Linear

Input projection.

conv_weight: Tensor

Depthwise kernel [dim, 3].

conv_bias: Tensor

Bias [dim].

out_proj: Linear

Output projection.

Implementations

impl Lfm2Conv

pub fn forward(&self, engine: &ComputeEngine, x: &Tensor) -> Tensor

Applies the operator to x.

pub fn params(&self) -> Vec<Tensor>

Trainable tensors (weights, then any LoRA adapters).

pub fn lora_params(&self) -> Vec<Tensor>

Only the LoRA adapter tensors (what LoRA fine-tuning updates).

pub fn named_params(&self, prefix: &str) -> HashMap<String, Tensor>

Parameters keyed by Hugging Face-style names under prefix.

pub fn named_lora_params(&self, prefix: &str) -> HashMap<String, Tensor>

LoRA tensors keyed by name under prefix.