Add basic 2D layer_norm operator

[xenova]

Needed for nomic-ai/nomic-embed-text-v1.5.

Example usage:

import { pipeline, layer_norm } from '@xenova/transformers';

// Create a feature extraction pipeline
const extractor = await pipeline('feature-extraction', 'nomic-ai/nomic-embed-text-v1.5', {
    quantized: false, // Comment out this line to use the quantized version
});

// Compute sentence embeddings
const texts = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'];
let embeddings = await extractor(texts, { pooling: 'mean' });

const matryoshka_dim = 512;
embeddings = layer_norm(embeddings, [embeddings.dims[1]])
    .slice(null, [0, matryoshka_dim])
    .normalize(2, -1);
console.log(embeddings.tolist());
// [
//   [-0.00518727907910943,   0.06514579057693481,  -0.21559129655361176, ...],
//   [-0.008253306150436401,  0.005108598619699478,   -0.22179779410362244, ...],
// ]

Relevant discussion: https://huggingface.co/nomic-ai/nomic-embed-text-v1.5/discussions/4#65cce8d0c52afc14ceac26c2

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.