Language Models are not restricted to natural language

[cmungall]

aio:LanguageModel ! Language Model "A model designed to predict the next word in a sequence or assign probabilities to sequences of words in natural language."

language models are also applied to protein sequences etc

Also the definition is technically long, because tokens != words in NL.

we could solve this with a triad pattern

• LM
  • Natural Language LM
  • Protein LM
  • ...

But this is overkill

Recommendation: change text to

A model designed to predict the next token in a sequence or assign probabilities to sequences of tokens in natural language or language-like structure