Method LayerNorm

Namespace

Qavren.Edge.Embeddings.Onnx

Assembly

Qavren.Edge.Embeddings.Onnx.dll

LayerNorm(Span<float>, float)

Mean/variance normalisation over the pooled vector, matching PyTorch F.layer_norm(x, (dim,)) with no learned weight or bias: subtract the mean, divide by sqrt(variance + epsilon). Required by nomic-embed-text-v1.5 and by nothing else here; see PostPoolLayerNorm.

public static void LayerNorm(Span<float> vector, float epsilon)

Parameters

vector Span<float>

The pooled vector, normalised in place.

epsilon float

The variance floor. 1e-5 is PyTorch's default.