HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Comment by mikodin | Hacker News Reader
Parent
Full thread
mikodin
·
What are the models? I am super curious in these as well
View on HN
simcop2387
·
Probably Kev and/or the decider models. Kev is trained on one of the 4B qwen models, similar for decider but it ranges from 0.8B through to the 35B-A3B model so far I believe.
Reply on news.ycombinator.com