ZYN: Zero-Shot Reward Models with Yes-No Questions
-
Updated
Aug 15, 2023 - Python
#
trlx
Here are 3 public repositories matching this topic...
Official code for "Unsupervised Text Style Transfer with Controllable Intensity" — a two-stage SFT + PPO framework for fine-grained control over text readability and sentiment transfer.
nlp reinforcement-learning sentiment transformers readability ppo sft text-style-transfer deepspeed controllable-text-generation trlx
-
Updated
Mar 28, 2026 - Python
Improve this page
Add a description, image, and links to the trlx topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the trlx topic, visit your repo's landing page and select "manage topics."