News for hackers. Stuff that matters.
Re:Phi-3 Technical Report by woodson on Tuesday April 23, 2024 @12:44PM (#40133979)
Especially for small models I had very bad results for use in translation. Even trying all kinds of tricks didn’t help (apparently prompting in the target language helps for some). Encoder-decoder models such as FLAN-T5 or MADLAD-400 seemed far superior at equal or even smaller model size.
Re:Phi-3 Technical Report by andai on Tuesday April 23, 2024 @03:19PM (#40136036)
I forget which model (LLaMA 3?) but I heard 95% of the training data was English.