Sign in

Mozhdeh Gheini

@mgheini.bsky.social
360 followers 410 following 6 posts

USC Graduate Student | USC ISI NLP Researcher | 3x Apple Intern | Self-proclaimed Michelin 3-star Foodie | she/her

PostsRepliesMedia
Mozhdeh Gheini @mgheini.bsky.social · 07/01/2025
I must also add that I’m assuming there’s no breakthrough architecture/pre-training/post-training method that pushes us to start everything from scratch. I’m simply asking about the decision factors in greenlighting such a full restart in the current status quo.
010
Mozhdeh Gheini @mgheini.bsky.social · 07/01/2025
Are there any good pointers on when/why one would decide to run pre-training from scratch (and follow it with post-training ofc) to create a fresh LLM? Is it simply about shifting the knowledge cutoff or more than that? Do we know how/if that happens nowadays? What are the deciding factors?
100
Reposted by Mozhdeh Gheini
Yoav Goldberg @yoavgo.bsky.social · 05/01/2025
i was annoyed at having many chrome tabs with PDF papers having uninformative titles, so i created a small chrome extension to fix it. i'm using it for a while now, works well. today i put it on github. enjoy. github.com/yoavg/pdf-ta...
59822
Mozhdeh Gheini @mgheini.bsky.social · 06/12/2024
Given how bad I am at it, it’s out of my league too; still fun though 😅
010
Mozhdeh Gheini @mgheini.bsky.social · 05/12/2024
Were you doing the NYT’s crossword? That’s how it happened for me. Also, if you want a bonus one, “doe” :)
110
Mozhdeh Gheini @mgheini.bsky.social · 03/12/2024
f’ as in fine-tuned from f, not the derivative of f 😅
010
Mozhdeh Gheini @mgheini.bsky.social · 03/12/2024
I got confused there yoo. Maybe something like “further condition the model’s output” (instead of update the model)? So if the model is f(x), before the dashed line it’s f’(x), and after that it’s f(x|prompt/context).
120
Reposted by Mozhdeh Gheini
Matthew Finlayson @mattf.nl · 12/11/2024
USC NLP folks are on Bluesky! Follow my amazing colleagues here go.bsky.app/KUwSZ6W
3175