ziyunli

ziyunli on Hacker News

Re:Writing an LLM from scratch, part 22 – training our LLM on Thursday October 16, 2025 @01:56PM (#45608580)

seems like you can filter by tag https://www.gilesthomas.com/llm-from-scratch

Software Design by Example: a tool-based introduction with Python

Posted by ziyunli on Tuesday July 25, 2023 @02:59PM
from the third-bit.com dept.

https://third-bit.com/sdxpy/

( Read More... | 1 comment | on HN )

The “it” in AI models is the dataset

Posted by ziyunli on Monday June 12, 2023 @02:29AM
from the nonint.com dept.

https://nonint.com/2023/06/10/the-it-in-ai-models-is-the-dataset/

( Read More... | 1 comment | on HN )

Re:Transformers from Scratch on Wednesday April 26, 2023 @01:38PM (#35717371)

There is a newer version of the second article https://nlp.seas.harvard.edu/annotated-transformer/

Re:Raft Consensus Animated (2014) on Wednesday August 17, 2022 @01:55PM (#32499595)

I am working on MIT 6.824[0] by myself as a side project. This visualization is very very helpful at the beginning just so that I can build up the right mental model and understand how components interact with each others.

[0]: https://nil.csail.mit.edu/6.824/2020/schedule.html