I brought a group together to do this class using the YouTube videos and course materials available online. It is challenging but rewarding. We tackled it one lecture video per week. Started with over 30 learners and by last session we were down to 8.
meken 1 hours ago [-]
I have fond memories of cs224d [1] taught by richardsocher. It’s a bit dated now as it was created in the pre-transformer era, but it was very cool introduction to applying deep learning to nlp at the time.
Similar thoughts here. That was when I realized the potential of the Internet: I didn't have to be a grad student at a tier 1 research university to learn about the frontier.
skerit 56 minutes ago [-]
> GPU compute for self-study
Those suggestions they make for a B200 start at $4.99 an hour.
Is that really required, for starting out?
I've been tinkering with my own from-scratch LLM, but in the early phases I don't need anything more than a 4090 on Vast.ai
flakiness 29 seconds ago [-]
I beliee these are affordable enough for the intended audience (which is Stanford undergrad/master)
root-parent 29 minutes ago [-]
You dont even need a GPU to train your own LLM.
airstrike 38 minutes ago [-]
I wonder if people prefer to learn this on their own or if building a community around open learning is something that others are interested in
storus 2 hours ago [-]
Thanks for releasing this again! What are this year's changes to prior offerings?
[1] https://cs224d.stanford.edu
Those suggestions they make for a B200 start at $4.99 an hour.
Is that really required, for starting out? I've been tinkering with my own from-scratch LLM, but in the early phases I don't need anything more than a 4090 on Vast.ai