sci-ml/trl
Train transformer language models with reinforcement learning (SFT, DPO, GRPO)
Screenshots
View
Download
BrowseChangeLog
commit 2216e94dd66856c8f19038918196535d276fa390
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sat Jul 4 13:24:24 2026 +0200
sci-ml/trl: new package, add 1.7.1
Reinforcement-learning fine-tuning for transformer LMs (SFT/DPO/GRPO), part of
the LlamaFactory dependency cluster. Pure-Python (setuptools); build+install and
import verified.
Author: Ivan S. Titov <iohann.s.titov@gmail.com>
Date: Sat Jul 4 13:24:24 2026 +0200
sci-ml/trl: new package, add 1.7.1
Reinforcement-learning fine-tuning for transformer LMs (SFT/DPO/GRPO), part of
the LlamaFactory dependency cluster. Pure-Python (setuptools); build+install and
import verified.