SOURCE REVIEWED / 2026-11-20
TRL
Inspect post-training trainers and the public harness-adapter recipe.
Where it fits
See upstream pinned runtime and hardware requirements
Train transformer language models with reinforcement learning.
License and practical limits
Apache-2.0. Training examples can require paidaccelerators,models and task environments under separate terms. Nothing has been provisioned or run by us.
Source reviewed;not independently installed or tested. No cloud service or hardware purchase is required to read the source.
Repository snapshot
19,779 stars and 3,162 forks when checked 2026-11-20. These numbers change and are not a security or quality endorsement.
Read the official repository ↗
Before you run it
Read installation requirements and release notes, verify the download source, and keep your own projects backed up. Review third-party plugins and model licenses separately.