Open Models Almanac
Methodsoptimizationtraining precision

implementation detail · filed under optimization

FP8-precision reinforcement learning

Reinforcement-learning training performed in FP8 precision.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See training precision for the methods filed beside it.

Also called RL was done in FP8 precision.

sources
2
model
1
lab adopt it
1
strongest
used

Documented in

Poolside

Evidence

2 quotes from 2 sources, one card per model, each opening with its strongest.

How sources treat it
used 2

Laguna-S-2.1

Poolsideadopted2 sources

S 2.1 is also our first model where RL was done in FP8 precision, accelerating that part of the training.

usedsoftware implementationin Laguna S 2.1Poolside
1 more from this model

It is the first Poolside model where reinforcement learning ran in FP8 precision.

usedpost trainingin Laguna S 2.1Poolside
↑