Re:Better and Faster Large Language Models via Multi-Token P...
by renonce on Wednesday May 01, 2024 @12:37PM
(#40225643)
Yeah but the other side of the coin is that they only explain the very basic concepts that are already settled for several years, not any of these "latest trends"
Re:Better and Faster Large Language Models via Multi-Token P...
by objektif on Wednesday May 01, 2024 @02:20PM
(#40227108)
Which latest trends you mean?
Re:Better and Faster Large Language Models via Multi-Token P...
by renonce on Thursday May 02, 2024 @04:09AM
(#40233833)
Anything that is not settled for several years, like papers published last year or so. Like RingAttention, quantization/pruning, rotary embedding, distillation, RLHF, L2 regularization, multimodal, MoE etc.
As an outsider but avid reader of this stuff linked from HN, I would recommend the channel 3blue1brown. He's got several NN and AI related videos, and the couple I've seen were pretty good.
https://www.youtube.com/watch?v=aircAruvnKk