Candle cross-encoder model support

@LaurentMazare
How can I use candle for a cross-encoder from sentence-transformers models (msmarco models: e.g. msmarco-distilroberta-base-v3)?

Does it require differents stack of implementation or can I just use the Bert example as for the embedding example?

Start by reviewing Candle's Bert example and embedding example, then compare them with the sentence-transformers cross-encoder models named in the issue, including msmarco-distilroberta-base-v3. Done would mean establishing whether Candle can support this model and documenting or implementing the required usage.

Written by the indexing model from the issue text.