Update pipelines.js to allow for `token_embeddings` as well (#770)
* Update pipelines.js to allow for `token_embeddings` as well
In recent examples of optimum pipeline export the feature extraction pipelines have their output state as `token_embeddings` instead of `last_hidden_state`.
So we should support this as well.
* Keep diff small
* Keep diff small
---------
Co-authored-by: Joshua Lochner <admin@xenova.com>