.. trained GPT-2 from scratch, kept all 32 checkpoints, and asked each “Who painted the Mona Lisa?”
Step 0: gibberish
Step 6k: “a very beautiful painting”
Final: “Leonardo da Vinci… in the early 14th century” 😅
Built on @karpathy’s recipe. Ask yours:
https://t.co/drX0dn5eeN
When does a language model learn that water 💧 is a liquid
I'm training GPT-2 (124M) live on one @nvidia RTX A5000 to learn. It's my 🏌️♂️ simulator :)
Every step, watt and checkpoint is public, and you can talk to any checkpoint.
https://t.co/DqOSqSvWx8
Part of why I joined @ClickHouseDB is because they do what I would do if I were running a database company.
✅Kept flagship OLAP DBMS open source. No enshitification.
✅Add verticals (agents, observability) on top of OLAP DBMS.
✅Launch Postgres service 1yr after buying PeerDB.
When you talked to Virginia Mason and UW Medical, curious what they said about how M4A would impact them and their care for residents of the state of Washington
Can you share with us what they said ?
Have you dynamically modeled the impact of M4A on leading Washington state hospitals and their patients ?
Have you done any work on whether Direct Contracting is the way to go to reduce OOP costs for patients and employers ?
Just trying to learn more. TIA !
@deedydas What about input bias / nothing wrong with it - but some of them may get students from background who have an starting advantage
This is why I always want to ask the compound question of - what is the best university for someone with my background looking for X outcome