Quantization paper explained || How it reduces computation and makes LLM training efficient
Hii,
Today we are reviewing the paper - Quantization.
Link to the paper - https://arxiv.org/pdf/1712.05877
Do listen in 2 x to save your time and get the most out of the video in the shortest amount of time possible.
Also I would recommend, dive deep and look into the mathematical details.
Some more recourses :
Video by Umar Jamil - https://www.youtube.com/watch?v=0VdNflU08yA
Watch on YouTube ↗
(saves to browser)
DeepCamp AI