blog-explorers (Blog-explorers)

posted an update 4 days ago

Post

2561

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

sergiopaniego

posted an update 10 days ago

Post

1853

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

sergiopaniego

posted an update 10 days ago

Post

826

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

s3nh

posted an update 12 days ago

Post

439

Eduhelp with more empathy, based on model finetuned on
psychotheraputic preferences just landed on

Beck-8B as a base model, 13000 steps on educational dataset.
Time to go further and build more 🥰
s3nh/EduHelp_Beck_8B
Thanks to @basilic_ai for computations <3

sergiopaniego

posted an update 13 days ago

Post

2261

@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

s3nh

posted an update 13 days ago

Post

4015

Just tried to create an educational assistant for younger people who can struggle with visualsation of 'what is this sorcery all about'.
Its first step of my spare time projects, sft on Qwen3-8B,

EduHelper is a child-friendly tutoring assistant fine-tuned from the Qwen3-8B base model using parameter-efficient fine-tuning (PEFT) with LoRA on the ajibawa-2023/Education-Young-Children dataset.

s3nh/EduHelp-8B

Glad to share my work, have a wonderful day!

2 replies

·

vumichien

authored 2 papers 14 days ago

MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources

Paper • 2509.25531 • Published 28 days ago • 7

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Paper • 2510.08697 • Published 18 days ago • 32

sergiopaniego

posted an update 18 days ago

Post

1442

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/

sergiopaniego

posted an update 21 days ago

Post

2390

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

·

sergiopaniego

posted an update 22 days ago

Post

2879

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

sergiopaniego

posted an update 27 days ago

Post

580

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

sergiopaniego

posted an update about 1 month ago

Post

483

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

sergiopaniego

posted an update about 1 month ago

Post

473

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!

sergiopaniego

posted an update about 1 month ago

Post

3451

💥 Tons of new material just landed in the smol-course! 🧑‍💻

> evaluation
> alignment
> VLMs
> quizzes
> assignments!
> certificates!👩‍🎓

go learn! 👉 https://huggingface.co/learn/smol-course/unit0/1

1 reply

·

ozayezerceli

authored a paper about 1 month ago

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

Paper • 2509.17671 • Published Sep 22 • 9

sergiopaniego

posted an update about 1 month ago

Post

1391

This summer TRL leveled up for multimodal alignment 🌞

✅ New VLM alignment methods (MPO, GRPO, GSPO)
✅ Extended RLOO & Online DPO for VLMs
✅ Native SFT support
✅ Ready-to-use training scripts

🔗 https://huggingface.co/blog/trl-vlm-alignment

innovation64

authored a paper about 1 month ago

CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering

Paper • 2502.01523 • Published Feb 3 • 2

Tonic

posted an update about 1 month ago

Post

690

the french ministry of culture releases their first conversation datasets on huggingface 👇🏻
ministere-culture/comparia-conversations

vikhyatk

posted an update about 1 month ago

Post

4155

Just released a preview of Moondream 3! moondream/moondream3-preview

This is a 9B parameter, 2B active MoE VLM with state of the art visual reasoning capabilities.

More details in the release blog post: https://moondream.ai/blog/moondream-3-preview

3 replies

·

Blog-explorers

AI & ML interests

Recent Activity

MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering

AI & ML interests

Recent Activity

Team members 751

blog-explorers's activity