News for hackers. Stuff that matters.
Re:Transformers Can Do Arithmetic with the Right Embeddings by asgeir on Tuesday May 28, 2024 @07:08AM (#40499502)
In my experience, LLMs tend to perform better if you give them instructions before the data to be operated on. At least for the ~13b size models.

So,something like: Please count the number of words in the following sentence. "What is the number of words in the sentence coming before the next one?"

edit: Which might be an artifact of the training data always being in that kind of format.

There are no comments on this comment yet.