llama : remove notion of CLS token

[ggerganov]

target #11062

My understanding is that there is no need to distinguish between BOS and CLS tokens, so we can simplify the implementation logic by removing CLS.

[danbev]

So this is only about the CLS token itself, which is not used in decoders hence only the BOS is needed, and has nothing to do with the pooling type CLS right?

[ggerganov]

So this is only about the CLS token itself, which is not used in decoders hence only the BOS is needed, and has nothing to do with the pooling type CLS right?

Yes, this is not related to the pooling types. We haven't used the CLS token in any of the examples yet, so I think this is a safe change.