Sign in

Quentin Gallouédec

@qgallouedec.hf.co
940 followers 170 following 17 posts

PhD - Research @hf.co 🤗 TRL maintainer

PostsRepliesMedia
Quentin Gallouédec @qgallouedec.hf.co · 03/05/2025
It started as a modest project to offer a free, open-source alternative to MuJoCo environments, and today, panda-gym is downloaded over 100k times, and cited in over 100 papers. 🦾
071
Quentin Gallouédec @qgallouedec.hf.co · 26/04/2025
just pip install trl
040
Quentin Gallouédec @qgallouedec.hf.co · 30/01/2025
🚀 TRL 0.14 – Featuring GRPO! 🚀 TRL 0.14 brings *GRPO*, the RL algorithm behind 🐳 DeekSeek-R1 . ⚡ Blazing fast generation with vLLM integration. 📉 Optimized training with DeepSpeed ZeRO 1/2/3.
040
Quentin Gallouédec @qgallouedec.hf.co · 22/01/2025
The algorithm behind DeepSeek's R1 model (aka GRPO) now lives in TRL main branch! Go and test it!
040
Quentin Gallouédec @qgallouedec.hf.co · 06/01/2025
[Stonks] TRL is a Python library for training language models. It has seen impressive growth this year. Lots of new features, an improved codebase, and this has translated into increased usage. You can count on us to do even more in 2025.
010
Quentin Gallouédec @qgallouedec.hf.co · 24/12/2024
🎅 Santa Claus has delivered the ultimate guide to understand OOM error (link in comment)
2165
Quentin Gallouédec @qgallouedec.hf.co · 17/12/2024
Top 1 Python dev today. Third time since september 🫨
040
Quentin Gallouédec @qgallouedec.hf.co · 17/12/2024
🚨 TRL 0.13 is out! 🤗 Featuring a Process-supervised Reward Models (PRM) Trainer 🏋️ PRMs empower LLMs to "think before answering"—a key feature behind OpenAI's o1 launch just two weeks ago. 🚀
010
Quentin Gallouédec @qgallouedec.hf.co · 03/12/2024
The number of TRL models on the 🤗 Hub has risen x60 this year! 📈 How about doing the same next year?
020
Quentin Gallouédec @qgallouedec.hf.co · 27/11/2024
Join us at Hugging Face as an intern if you want to contribute to amazing open-source projects, and develop LLM's best finetuning library, aka TRL. 🧑‍💻 Full remote 🤯 Exciting subjects 🌍 Anywhere in the world 🤸🏻 Flexible working hours Link to apply in comment 👇
170