Hugging Face's logo
Activity Feed

AI & ML interests

Aligning LLMs to be helpful, honest, harmless, and huggy (H4)

Recent Activity
edbeeching  updated a model 9 days ago
HuggingFaceH4/Qwen3-4B-Thinking-2507-SFT-tr5
edbeeching  published a model 10 days ago
HuggingFaceH4/Qwen3-4B-Thinking-2507-SFT-tr5
clefourrier  authored a paper 18 days ago
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
View all activity
qgallouedec 
posted an update 24 minutes ago
view post
Post
TRL v1.0 is out!

Hugging Face's TRL library is downloaded 3 million times a month. Over 130k models trained with it are public on the Hub, and major projects like @unsloth and @axolotl-ai-co build directly on top of it. v1.0 is the moment we acknowledged that responsibility explicitly, with a real stability contract.

The field hasn't settled. Building stable software in a domain that keeps invalidating its own assumptions is the actual problem we're solving. The answer is a design that can absorb the next shift without breaking what people rely on.

What's in v1.0:
Deep Hugging Face integration, low infrastructure burden
What's next: asynchronous GRPO, better scaling support, and making training legible enough that agents can inspect and steer it.

pip install --upgrade trl


Read more: hf.co/blog/trl-v1
mishig 
posted an update 5 days ago
edbeeching 
updated a model 9 days ago
edbeeching 
published a model 10 days ago
sergiopaniego 
posted an update 18 days ago
view post
Post
663
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 18 days ago
sergiopaniego 
posted an update 19 days ago
view post
Post
372
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 20 days ago
view post
Post
359
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
cmpatino 
in HuggingFaceH4/on-policy-distillation 26 days ago

How to reproduce the results in your blog?

13
#7 opened 2 months ago by
141forever
alvarobartt 
posted an update 26 days ago
view post
Post
3451
Learn how to deploy Microsoft Research VibeVoice ASR on Microsoft Azure Foundry with Hugging Face to generate rich audio transcriptions with Who, When, and What! 💥

> 🕒 60-minute single-pass processing, no chunking or stitching
> 👤 Customized hotwords to guide recognition on domain-specific content
> 📝 Rich transcription: joint ASR + diarization + timestamping in one pass
> 🌍 50+ languages with automatic detection and code-switching support
> 🤗 Deployed on Microsoft Foundry via an OpenAI-compatible Chat Completions API

https://huggingface.co/docs/microsoft-azure/foundry/examples/deploy-vibevoice-asr
sergiopaniego 
posted an update 28 days ago
view post
Post
595
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 29 days ago
sayakpaul 
authored 2 papers 29 days ago
sergiopaniego 
posted an update about 1 month ago
view post
Post
2437
What happens when you make an LLM drive a car where physics are real and actions can't be undone?

I ported CARLA, the autonomous driving simulator, to OpenEnv and added training support via TRL + Hugging Face Spaces.

The model interacts with the simulator through tool calls (observe, brake, change lane) and learns from a reward signal.

In 50 training steps, Qwen 0.6B learns to swerve and brake to avoid pedestrians in emergency situations.

The project supports text and vision (VLMs can see through a camera sensor), open-world driving with traffic, and multiple driving scenarios.

This builds on the carla-env project by sinatras, which originally placed LLMs inside CARLA for evaluation. We extended it with vision, new scenarios, rubric-based rewards, and made it trainable end-to-end.

Blog: https://huggingface.co/blog/sergiopaniego/bringing-carla-to-openenv-trl/
CARLA env in OpenEnv: https://github.com/meta-pytorch/OpenEnv/tree/main/envs/carla_env
Training script: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/carla.py
albertvillanova 
posted an update about 1 month ago
view post
Post
2172
🚀 TRL v0.29.0 introduces trl-training: an agent-native training skill.

This makes the TRL CLI a structured, agent-readable capability, allowing AI agents to reliably execute training workflows such as:
- Supervised Fine-Tuning (SFT)
- Direct Preference Optimization (DPO)
- Group Relative Policy Optimization (GRPO)

We’re excited to see what the community builds on top of this.

If you’re working on AI agents, alignment research, or scalable RL training infrastructure: give TRL v0.29.0 a try! 🤗

The future of ML tooling is agent-native.
🔗 https://github.com/huggingface/trl/releases/tag/v0.29.0
sayakpaul 
submitted a paper to Daily Papers about 1 month ago
sayakpaul 
authored a paper about 1 month ago
qgallouedec 
posted an update about 1 month ago
view post
Post
2940
@CohereLabs just released 🌿 Tiny Aya: a fully open-source 3B parameter model that speaks 70+ languages 🌍! But there’s a catch:

Tiny Aya is just a language model. It doesn’t support tool calling, the key capability that turns frontier models into powerful *agents*.
So the real question is:

How hard is it to turn Tiny Aya into an agent?

Turns out… it’s simple, thanks to Hugging Face TRL.
We’re sharing a hands-on example showing how to train Tiny Aya to turn it into a tool-calling agent using TRL, unlocking what could become the first *massively multilingual open agent*.

Small model. Global reach. Agent capabilities.

👉 https://github.com/huggingface/trl/blob/main/examples/notebooks/sft_tool_calling.ipynb
  • 1 reply
·
sergiopaniego 
posted an update about 1 month ago