sergiopaniego (Sergio Paniego)

posted an update 2 days ago

Post

1307

nanochat is now in transformers!

The LLM by @karpathy is officially in the library, and we wrote a blog covering: how did we port the model, differences from the original, and how to run or train it.

go read it 🤓

nanochat-students/transformers

posted an update 4 days ago

Post

3821

you gotta go fast and go read the latest blog by @ror et al. explaining Continuous Batching in depth

https://huggingface.co/blog/continuous_batching

posted an update 6 days ago

Post

1621

Interested in RL training environments?

We just released a beginner-friendly walkthrough notebook!

Train a model to play Wordle using TRL + OpenEnv (TextArena) + GRPO + vLLM.

happy learning! 🌱

Notebook: https://github.com/huggingface/trl/blob/main/examples/notebooks/openenv_wordle_grpo.ipynb

OpenEnv guide in TRL: https://huggingface.co/docs/trl/main/en/openenv

posted an update 10 days ago

Post

271

Ya está disponible el vídeo de la charla del otro día en @nerdearla sobre IA abierta, por si queréis verla! 🤠

https://www.youtube.com/watch?v=p-JLn4xAkMw

1 reply

·

posted an update 10 days ago

Post

2522

we've just added several example scripts to TRL showing how to train models with GRPO using some of the new OpenEnv environments

train a model to interact with a browser (🎮 BrowserGym Env), play Wordle (🎮 Wordle Env) and moooore!

TRL (GRPO + vLLM) + OpenEnv! ⚡️

📝 go play with them: https://github.com/huggingface/trl/tree/main/examples/scripts/openenv

📝 examples list: https://huggingface.co/docs/trl/main/en/example_overview#scripts

posted an update 12 days ago

Post

1705

Who wants a TRL sticker? 🙋

https://github.com/huggingface/trl

1 reply

·

posted an update 25 days ago

Post

5338

fine-tuning a 14B model with TRL + SFT on a free Colab (T4 GPU)?
thanks to the latest TRL optimizations, you actually can!
sharing a new notebook showing how to do it 😎

colab: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_trl_lora_qlora.ipynb

notebooks in TRL: https://github.com/huggingface/trl/tree/main/examples/notebooks

2 replies

·

posted an update 27 days ago

Post

428

Gave a smol 🤏 intro to Agents using smolagents last Monday!
Sharing the slides in case you're curious. They serve as a gentle first step into the Agents Course we developed at @huggingface 🫶🫶

Course: https://huggingface.co/learn/agents-course/unit0/introduction

Workshop material: https://github.com/sergiopaniego/talks/tree/main/intro_to_agents

posted an update 30 days ago

Post

3116

Sharing the slides from yesterday's talk about "Fine Tuning with TRL" from the @TogetherAgent x @huggingface workshop we hosted in our Paris office 🎃!

Link: https://github.com/sergiopaniego/talks/blob/main/fine_tuning_with_trl/Fine%20tuning%20with%20TRL%20(Oct%2025).pdf

posted an update about 1 month ago

Post

414

On-Policy distillation is trendy! and super useful!

HuggingFaceH4/on-policy-distillation

posted an update about 1 month ago

Post

2881

Meet OpenEnv 👋, an open ecosystem of environments for intelligent agents. Build, share, and test agents safely and consistently.

Ideal for training with TRL (we include examples🤓), deployment, and community collaboration via the HF Hub

Blog: https://huggingface.co/blog/openenv
Hub for Environments:

openenv
OpenEnv repo: https://github.com/meta-pytorch/OpenEnv
Try it out using TRL: https://huggingface.co/docs/trl/main/en/openenv

1 reply

·

posted an update about 1 month ago

Post

1963

New drop! 💥 The VLM Object Understanding Comparison Space now runs with Qwen3-VL-4B and moondream3.

You can compare how models reason about images 🧠

Bonus: thanks to @ariG23498 , you now get auto-suggested prompts to explore faster.

Let’s gooo

sergiopaniego/vlm_object_understanding

posted an update about 1 month ago

Post

911

New drop! 💥 The VLM Object Understanding Comparison Space now runs with Qwen3-VL-4B and moondream3.

You can compare how models reason about images 🧠

Bonus: thanks to @ariG23498 , you now get auto-suggested prompts to explore faster.

Let’s gooo

sergiopaniego/vlm_object_understanding

posted an update about 2 months ago

Post

2327

@Qwen released their new small and dense VLMs (Qwen3-VL).

They're incredibly capable and one of my all-time favourite VLMs.

🤗 We’ve prepared some resources to help you get started.

> Fine-tune Qwen3-VL-4B with SFT or GRPO (free Colab notebooks):
> SFT: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_qwen_vl.ipynb
> GRPO: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_qwen3_vl.ipynb

> Compare object detection vs. Moondream3:
sergiopaniego/vlm_object_understanding

> Fine-tune from the CLI using TRL:
https://github.com/kashif/Qwen3-VL/blob/trl-sft/qwen-vl-finetune/README.md#trl-based-training-single-gpu

posted an update about 2 months ago

Post

1482

Super nice intro to fine-tuning with TRL, just dropped by @google (runs free on Colab)!

They use SFT + QLoRA to fine-tune the tiny Gemma 3 270M model for emoji generation

Here’s what the fine-tuned model generates for the prompt: “I'm learning to tweet” → 🐦🗣💻

Colab: https://colab.research.google.com/github/google-gemini/gemma-cookbook/blob/main/Demos/Emoji-Gemma-on-Web/resources/Fine_tune_Gemma_3_270M_for_emoji_generation.ipynb
Try it out: google/emoji-gemma
Learn more: https://developers.googleblog.com/en/own-your-ai-fine-tune-gemma-3-270m-for-on-device/

posted an update about 2 months ago

Post

2435

Online training methods (e.g., GRPO) require real-time generation, a compute- and memory-heavy bottleneck.

TRL has built-in vLLM support and in this new recipe, we show how to leverage it for efficient online training. Run on Colab ⚡, scale to multi-GPU/multi-node!

🧑‍🍳 recipe: https://huggingface.co/learn/cookbook/grpo_vllm_online_training

1 reply

·

posted an update about 2 months ago

Post

2921

A few days ago, Thinking Machines Lab released “LoRA Without Regret”, showing that LoRA can match full fine-tuning performance when configured right.

Naturally, we decided to reproduce the results with TRL and release a guide!

https://huggingface.co/docs/trl/main/en/lora_without_regret

posted an update about 2 months ago

Post

610

Want to deploy open models using vLLM as the inference engine?
We just released a step-by-step guide on how to do it with @huggingface Inference Endpoints, now available in the vLLM docs.

let the gpus go brrr

https://docs.vllm.ai/en/latest/deployment/frameworks/hf_inference_endpoints.html

posted an update 2 months ago

Post

504

You need to try this tool! 🫡

My colleague @Molbap built an interactive HF Space to explore the modular support of open models in transformers over time

👀 You’ll spot things like 🦙 llama defining many models or which ones could be modular next

Try it: Molbap/transformers-modular-refactor

posted an update 2 months ago

Post

495

How fast can you create an endpoint in Hugging Face Inference Endpoints with a new model + vLLM to deploy a state-of-the-art OCR model?

Let’s break it down step by step.

1️⃣ Create your endpoint
Go to Hugging Face Endpoints → + NEW
Select Deploy from Hub → rednote-hilab/dots.ocr → Configure 🛠️

2️⃣ Configure hardware & container
Pick hardware: AWS/GPU/L4 ⚡
Set container: vLLM 🐇
Click Create ✅

3️⃣ Update endpoint settings
Container: Container URI: vllm/vllm-openai:nightly → Update
Advanced: add flag --trust-remote-code → Update ⚠️

4️⃣ Run inference
Download the script 📝: ariG23498/useful-scripts
Set your HF_TOKEN and update base_url in the script.
Run it. ✅

Your OCR model is now live via HF Inference Endpoints!

Sergio Paniego PRO

AI & ML interests

Recent Activity

Organizations

Sergio Paniego PRO

AI & ML interests

Recent Activity

Organizations

sergiopaniego's activity