@srchvrs : I find it quite upsetting that people use the terms LLM, or PLM (pretrained LM) to denote every possible pre-trained Transformer model including BERT, T5, etc... This reminds me good old days when DNN was often used to denote a multilayer feedforward network (or at least this was • TwiCopy

Leo Boytsov

@srchvrs

+ Follow

Sr. Research Scientist @AWS Labs (ph-D @LTIatCMU) working on (un)natural language processing, speaking πtorch & C++. Opinions sampled from MY OWN 100T param LM.

ID: 87473622

linkhttp://searchivarius.org/about calendar_today04-11-2009 16:22:33

24,24K Tweet

8,8K Followers

1,1K Following

Leo Boytsov

@srchvrs

3 months ago

I find it quite upsetting that people use the terms LLM, or PLM (pretrained LM) to denote every possible pre-trained Transformer model including BERT, T5, etc... This reminds me good old days when DNN was often used to denote a multilayer feedforward network (or at least this was

thumb_up_off_alt10

chat_bubble_outline3

repeat0

shareShare