Example notebook with Datalab on a text dataset with sota LLM & embeddings model

[jwmueller]

Make a version of this tutorial: https://docs.cleanlab.ai/stable/tutorials/datalab/text.html but using more modern ML models. pred_probs can be produced by a (pretrained) LLM, and features produced via a recently popular Embeddings model.

Recommend using models from HuggingFace. Try to select a dataset where the detected issues are interesting, particularly one where the under-performing group issue is present.