🏗️ Building on HF

Pablo Montalvo PRO

Molbap

huggingface

·

molbap

AI & ML interests

Tensors, vision, data

Recent Activity

updated a bucket about 13 hours ago

Molbap/portal-repro-trackio-bucket

liked a Space about 16 hours ago

cetiennec/teaching

upvoted an article 8 days ago

Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident

View all activity

Organizations

liked a Space about 16 hours ago

Teaching

Slides, exercise sheets and interactive spaces of my courses

liked a Space 14 days ago

Steer a robot with words

Free text to a VLA through a VLM planner, in LeRobot

liked a Space about 1 month ago

World Models: The Simulation Strikes Back

The Simulation Strikes Back -- what even is a world model?

liked a Space about 2 months ago

How a Transformers Model Loads in vLLM

Animated walkthrough of vLLM's Transformers modeling backend

liked 2 models 3 months ago

allenai/Molmo2-8B

Image-Text-to-Text • 9B • Updated Jan 23 • 40.9k • 198

zai-org/GLM-5.2

Text Generation • 753B • Updated Sep 1 • 275k • • 5.19k

liked a model 4 months ago

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 17 days ago • 3.76M • 4.93k

liked a Space 4 months ago

physics-intern: an Autonomous Agent for Physics Research

Explore an autonomous AI workflow for physics research

liked a model 4 months ago

google/gemma-4-31B-it

Image-Text-to-Text • 31B • Updated Jul 20 • 8.45M • • 4.25k

liked a Space 5 months ago

Reachy Mini Debug & CI Testbench

Debug and CI validation testbench for Reachy Mini

liked a model 5 months ago

PaddlePaddle/PaddleOCR-VL-1.6

Image-Text-to-Text • 1.0B • Updated Aug 8 • 80.7k • 564

liked a Space 6 months ago

Baby Reachy-Mini Companion

A fully local Reachy Mini AI Companion for babies and kids.

liked 6 Spaces 11 months ago

The Jagged AI Frontier is a Data Frontier

Why AI capabilities are shaped by data availability

Maintain the unmaintainable

Explore the HuggingFace Transformers model dependency graph

2025 Wrapped

Generate Hugging Face Wrapped report for 2025

Open Object Detection Leaderboard

Request evaluation for a new model

The Eiffel Tower Llama

Explore the Eiffel Tower Llama experiment with open-source models

README

liked 2 Spaces 12 months ago

DeepSeek OCR 2 Demo

Try out DeepSeek-OCR-2 on your PDFs or images

The Smol Training Playbook

The secrets to building world-class LLMs