Loreon
Labs
Platform
Docs
Home
Ecosystems
Python
poke_local_llm_rl
this is all jippity nonsense pay it no mind
Python
Emerging
GitHub
Stars
1
Forks
—
Contributors
1
Last push
1mo ago
Recent commits
Latest commits.
add reqs
9568697
PWhiddy
1mo ago
bigger actually trains
7614f96
PWhiddy
1mo ago
better thunking
5346b8e
PWhiddy
1mo ago
pretrain, bigger model version, more kl loss, adjust prompt
83f5d3c
PWhiddy
1mo ago
actually trains to something but loses any kind of actual think
59dd074
PWhiddy
1mo ago
adjust rewards and envs
a57b10c
PWhiddy
1mo ago
actually generates valid actions sometimes
3f32f03
PWhiddy
1mo ago
adjust parse fail penalty, remove repeated action penalty
15c38ed
PWhiddy
1mo ago
Top contributors
Builders behind this project.
PWhiddy
11 commits
