TRL

JSON →
library 0.29.1 ·python
verified Jun 9, 2026 install stale

Hugging Face library for post-training LLMs: SFT, DPO, GRPO, PPO, reward modeling. Current version is 0.29.1 (Mar 2026). Requires Python >=3.10. Extremely high API churn — major parameter renames across versions. tokenizer= renamed to processing_class= in 0.12. Still pre-1.0 (Development Status: Pre-Alpha).

total hits 29
actors 9 distinct systems
last hit 1d ago Amazonbot
ByteDance
5
Amazonbot
4
MetaBot
4
GPTBot
3
ChatGPT-User
3
Script
2
OAI-SearchBot
1
Humans
2

top countries 🇺🇸 United States · 🇸🇬 Singapore · 🇨🇦 Canada · 🇩🇪 Germany · PT