Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
clefourrier  authored a paper 1 day ago
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
AdinaY  submitted a paper 1 day ago
Training Language Models via Neural Cellular Automata
sergiopaniego  updated a dataset 1 day ago
huggingface-projects/Deep-RL-Course-Certification
View all activity
sergiopaniego 
posted an update 1 day ago
view post
Post
97
ICYMI, great blog by @kashif and @stas on Ulysses Sequence Parallelism: train with million-token contexts

on 4×H100s: 12x longer sequences, 3.7x throughput

learn how to integrate it with Accelerate, Transformers, and TRL ⤵️
https://huggingface.co/blog/ulysses-sp
clefourrier 
authored a paper 1 day ago
AdinaY 
submitted a paper to Daily Papers 1 day ago
sergiopaniego 
updated a dataset 1 day ago
hysts 
updated a Space 1 day ago
sergiopaniego 
posted an update 2 days ago
view post
Post
116
We just released a big blog surveying 16 OSS frameworks for async RL training of LLMs!

We're building a new async GRPO trainer for TRL and as first step, we needed to understand how the ecosystem solves this problem today.

The problem: in synchronous RL training, generation dominates wall-clock time. 32K-token rollouts on a 32B model take hours while training GPUs sit completely idle. With reasoning models and agentic RL making rollouts longer and more variable, this only gets worse.

The ecosystem converged on the same fix: separate inference + training onto different GPU pools, rollout buffer, and async weight sync.

We compared 16 frameworks across 7 axes: orchestration, buffer design, weight sync, staleness management, partial rollouts, LoRA, and MoE support.

This survey is step one. The async GRPO trainer for TRL is next!

https://huggingface.co/blog/async-rl-training-landscape
sergiopaniego 
posted an update 3 days ago
view post
Post
183
Nemotron 3 Super by @nvidia is here! NVIDIA's hybrid Mamba2/Transformer models are now natively supported in transformers (no trust_remote_code needed)

Fine-tune them with TRL in just a few lines of code. Notebook + script included to get started right away. goooo!

- Notebook: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_nemotron_3.ipynb
- Script: https://github.com/huggingface/trl/blob/main/examples/scripts/sft_nemotron_3.py
- Collection with all the models: https://huggingface.co/collections/nvidia/nvidia-nemotron-v3
pcuenq 
updated a dataset 3 days ago
AdinaY 
submitted a paper to Daily Papers 5 days ago
hysts 
updated 7 Spaces 7 days ago
sergiopaniego 
posted an update 11 days ago
view post
Post
470
did you know you can train agentic models with RL deploying the environments on HF Spaces? 🤗

with TRL + OpenEnv, your training script connects to remote environments hosted as Spaces

want to train faster? → just add more Spaces (TRL handles the parallelization natively)

we used this to train a model to solve the trolley problem in CARLA. 2 HF Spaces running a full driving simulator, each on a T4 GPU

full write-up with code and results → https://huggingface.co/blog/sergiopaniego/bringing-carla-to-openenv-trl
sergiopaniego 
posted an update 12 days ago
sayakpaul 
authored 2 papers 12 days ago