Today we're releasing prime-rl v0.10.0 and verifiers v0.4.0
We added our new RL algorithm IPO as the default, tailored for async RL stability, as well as performance improvements and new model support
Prime Intellect releases prime-rl v0.10.0 and verifiers v0.4.0
AISummary
The update makes its new RL algorithm IPO the default, tailored for async RL stability, and adds performance improvements and new model support.
Post on XView on X
Source: Prime Intellect · x.comPublished