huggingface / trl

Train transformer language models with reinforcement learning.
http://hf.co/docs/trl
Apache License 2.0
9.56k stars 1.19k forks source link

Remove the leading space in the tldr preference dataset #1773

Closed vwxyzjn closed 3 months ago

vwxyzjn commented 3 months ago

Remove the leading space to be consistent with other TRL preference datasets.

HuggingFaceDocBuilderDev commented 3 months ago

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.