ggmlR (version 0.6.1)

ggml_norm: Layer Normalization (Graph)

Description

Creates a graph node for layer normalization. Normalizes input to zero mean and unit variance.

Usage

ggml_norm(ctx, a, eps = 1e-05)

Value

Tensor representing the layer normalization operation

Arguments

ctx

GGML context

a

Input tensor

eps

Epsilon value for numerical stability (default: 1e-5)

Examples

# \donttest{
ctx <- ggml_init(16 * 1024 * 1024)
a <- ggml_new_tensor_1d(ctx, GGML_TYPE_F32, 4)
ggml_set_f32(a, c(1, 2, 3, 4))
result <- ggml_norm(ctx, a, eps = 1e-5)
graph <- ggml_build_forward_expand(ctx, result)
ggml_graph_compute(ctx, graph)
ggml_get_f32(result)  # Normalized values
ggml_free(ctx)
# }