lets callers inject a prebuilt Tokenizer in the LanguageModel

[kashif]

fixes #238

[pcuenca]

Thanks @kashif! 🙌

I have some questions about the potentially confusing use of configuration and tokenizer, could we maybe make behaviour more explicit, or perhaps defer configuration to a later PR if it's not essential?

[kashif]

thanks! will look shortly and fix

[pcuenca]

Thank you!! 🙌