AI Radar
Support
LiveUpdated 2026-09-19 18:40 UTC

trl

trl — Train transformer language models with reinforcement learning. - huggingface/trl

trl is Train transformer language models with reinforcement learning. - huggingface/trl. It is ranked #650 on the AI Radar, in AI infra & evals, first seen 9 days ago and shared in 2 posts (7k views).

Visit github.com

What people said about trl on X

TRL v1.13 is out! our open-source RL training library to to post-train foundation models this new release is focusing on "long context training" with a new guide on how to post-train model with 1M+ token context https://huggingface.co/docs/trl/long_context_training + various improvements on speed and memory usage as…

@Thom_Wolf, 9 days ago · 30 likes · see the post

🎓 兄弟们,想把开源大模型微调成自己想要的样子,Hugging Face 官方维护的 TRL 把整套后训练都备好了。 GitHub 上 1.9 万 star,DeepSeek R1 训练用的 GRPO 算法,在 TRL 里就是一个现成的训练器。今天刚发 1.13 版,上一版是 8 月 26 号。 以前想照着论文给模型做一遍偏好对齐或者强化学习,得自己写训练循环、算奖励、处理多卡,光把代码跑通就要耗掉不少时间。 在 TRL 里,从监督微调 SFT,到用偏好数据做 DPO,再到 GRPO 强化学习,每一步都有对应的 Trainer 直接调,不想写代码还能用命令行起训练。 显卡不够也有办法:接上 PEFT 用 LoRA、QLoRA…

@Ryrenz, 8 days ago · 4 likes · see the post

Alternatives to trl

trl in numbers

FAQ

What is trl?

Train transformer language models with reinforcement learning. - huggingface/trl It was first shared on X 9 days ago and is ranked #650 on the AI Radar.

Is trl free?

It is open source.

Who shared trl?

2 accounts on X, including @Thom_Wolf, @Ryrenz, in 2 posts totalling 7k views.

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:40 UTC. Full method.