RL context-1 on tinker
#6
by ggouletlanglois - opened
Hi folks!
I really enjoyed your write-up! Super interesting and really well written!
I'd like to try tuning context-1 with RL on Tinker for a problem I'm working on. I know you used Tinker to train context-1, so I was wondering if you've shared the model checkpoint anywhere / or if you know a way to get this setup?
Thanks in advance!
ggouletlanglois changed discussion title from RL context-1 on thinker to RL context-1 on tinker