HackerTrans
TopNewTrendsCommentsPastAskShowJobs

kartoolOz

no profile record

Submissions

Show HN: Comparing various contrastive losses on text and vision embeddings

github.com
3 points·by kartoolOz·vor 2 Jahren·0 comments

comments

kartoolOz
·letztes Jahr·discuss
It's very hyper-parameter dependent, and in my testing didn't provide comparable performance to maxsim.
kartoolOz
·letztes Jahr·discuss
"कर्मण्येवाधिकारस्ते मा फलेषु कदाचन | मा कर्मफलहेतुर्भूर्मा ते सङ्गोऽस्त्वकर्मणि" - Bhagvad gita, chapter 2, verse 47.

You have a right to perform your prescribed duties, but you are not entitled to the fruits of your actions. Never consider yourself to be the cause of the results of your activities, nor be attached to inaction.
kartoolOz
·vor 2 Jahren·discuss
WebArena does this really well, called the "accessibility_tree" https://github.com/web-arena-x/webarena/blob/main/browser_en...
kartoolOz
·vor 2 Jahren·discuss
The Info extraction and Question Answering metrics are far worse than transformers though.

They also say that in the blog "However, both Based and Mamba still underperform the strongest Transformer baseline, sometimes by large margins. This is consistent with our “no free lunch” observation above"