Hugging Face's logo

TRL
https://github.com/huggingface/trl
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

qgallouedec  updated a dataset 2 days ago
trl-lib/documentation-images
sergiopaniego  updated a dataset 5 days ago
trl-lib/documentation-images
ShirinYamani  updated a dataset 16 days ago
trl-lib/documentation-images
View all activity

qgallouedec 
updated a dataset 2 days ago
sergiopaniego 
posted an update 4 days ago
view post
Post
3765
You can now supercharge your TRL training pipelines with kernels

👷 kernels is new library to load optimized compute kernels directly from the Hub

Combined with TRL, it makes you developer experience smoother & faster.

Check out the new guide to learn more! 🕺

Learn ➡️ https://huggingface.co/docs/trl/main/en/kernels_hub
sergiopaniego 
updated a dataset 5 days ago
sergiopaniego 
posted an update 12 days ago
view post
Post
405
It's now posible to do end-2-end ML without leaving the @huggingface Hub, by combining TRL + HF jobs + Trackio!!

🐡We just released a full guide explaining the process.

Go check it out!

📖 Guide: https://huggingface.co/docs/trl/main/en/jobs_training

💡 Reminder: HF Jobs is only available for Pro, Team, or Enterprise plans. Yet another reason to upgrade
ShirinYamani 
updated a dataset 16 days ago
qgallouedec 
updated 2 Spaces 21 days ago
qgallouedec 
published a Space 21 days ago
qgallouedec 
updated a dataset 23 days ago
sergiopaniego 
posted an update 27 days ago
sergiopaniego 
posted an update 28 days ago
view post
Post
405
New Zero-Shot Object Detectors in transformers! 🥽

We’ve added LLMDet and MM GroundingDINO, plus a demo Space to compare them with others 🖼️

Play with it: ariG23498/zero-shot-od
sergiopaniego 
posted an update 28 days ago
qgallouedec 
published a dataset about 1 month ago
sergiopaniego 
posted an update about 1 month ago
view post
Post
456
Latest TRL release brings major upgrades for multimodal alignment!

We dive into 3 new techniques to improve VLM post-training in our new blog:

🌋 GRPO
🎞️ GSPO
🐙 MPO
➕ vLLM integration for online training w/ transformers backend\

🐡 Blog: https://huggingface.co/blog/trl-vlm-alignment
sergiopaniego 
posted an update about 1 month ago
sergiopaniego 
posted an update about 1 month ago
view post
Post
3417
Want to learn how to align a Vision Language Model (VLM) for reasoning using GRPO and TRL? 🌋

🧑‍🍳 We've got you covered!!

NEW multimodal post training recipe to align a VLM using TRL in @HuggingFace 's Cookbook.

Go to the recipe 👉https://huggingface.co/learn/cookbook/fine_tuning_vlm_grpo_trl

Powered by the latest TRL v0.20 release, this recipe shows how to teach Qwen2.5-VL-3B-Instruct to reason over images 🌋
sergiopaniego 
posted an update about 1 month ago
view post
Post
4515
Just included example scripts for aligning models using GSPO (including VLM example) 🙆‍♂️🙆‍♂️

GSPO is the latest RL alignment algo by @Alibaba_Qwen and it's already supported in the latest TRL v0.20 release.

Super-easy-to-get-started example scripts below, GO run them!👩‍💻👩‍💻

🧑‍🎨 Script: https://github.com/huggingface/trl/blob/main/examples/scripts/gspo.py
🦄 VLM script: https://github.com/huggingface/trl/blob/main/examples/scripts/gspo_vlm.py
🧩 More TRL examples: https://huggingface.co/docs/trl/main/en/example_overview
🧙‍♂️ GSPO paper: Group Sequence Policy Optimization (2507.18071)
sergiopaniego 
posted an update about 1 month ago
view post
Post
346
Did you miss this? 👓

🧙‍♂️vLLM + transformers integration just got upgraded with direct VLM support.

Select a VLM + model_impl=transformers and play via vLLM!
sergiopaniego 
posted an update about 1 month ago
view post
Post
2687
We just released TRL v0.20 with major multimodal upgrades!

👁️ VLM support for GRPO (highly requested by the community!)
🎞️ New GSPO trainer (from @Qwen , released last week, VLM-ready)
🐙 New MPO trainer (multimodal by design, as in the paper)

📝 Full release notes here: https://github.com/huggingface/trl/releases/tag/v0.20.0
qgallouedec 
updated a Space about 1 month ago