While the model is meant as a research artifact, the accompanying blog post gives insights into the quirkinesses of (RL) training and is an interesting read.
Specs
Params9B
LicenseCC-BY-NC-4.0
Tags
modelsmodels/llmsartifacts/17
Related Models
While the model is meant as a research artifact, the accompanying blog post gives insights into the quirkinesses of (RL) training and is an interesting read.
