Rafael Magalhães PRO

rafaelmm

https://about.me/rafaelmm

AI & ML interests

AI projects as solutions to problems in engineering, health, business, etc..

Recent Activity

liked a model 24 days ago

fastino/gliner2-large-v1

upvoted a collection 24 days ago

gliner2 family

liked a Space about 1 month ago

HuggingFaceTB/smol-training-playbook

View all activity

Organizations

liked a model 24 days ago

fastino/gliner2-large-v1

Updated Nov 25 • 13.6k • 26

upvoted a collection 24 days ago

gliner2 family

Collection

GLiNER2 extends the original GLiNER architecture to support multi-task information extraction with a schema-driven interface. This base model provides • 4 items • Updated 23 days ago • 16

liked a Space about 1 month ago

The Smol Training Playbook

📚

2.7k

The secrets to building world-class LLMs

updated a collection 5 months ago

Image to text experiments

Collection

2 items • Updated Aug 7

upvoted an article 7 months ago

Article

nanoVLM: The simplest repository to train your VLM in pure PyTorch

May 21

•

245

liked 5 Spaces 9 months ago

4M Demo

⚡

201

4M: Massively Multimodal Masked Modeling

MultiMAE

😻

Reconstruct images using masked autoencoders

Open Portuguese LLM Leaderboard

🏆

235

Track, rank and evaluate open LLMs in Portuguese

UniK3D Demo

🏢

UniK3D (CVPR 2025)

TripoSG

🔮

842

Generate 3D models from images

updated a Space 9 months ago

First Agent Template

⚡

Get time, sum numbers, and more with this versatile assistant

liked a model 10 months ago

stepfun-ai/GOT-OCR2_0

Image-Text-to-Text • 0.7B • Updated Feb 4 • 15.3k • 1.53k

upvoted a paper 10 months ago

YOLOE: Real-Time Seeing Anything

Paper • 2503.07465 • Published Mar 10 • 16

liked a Space 10 months ago

BFM Segmentation

🏃

Segment building materials and generate color palettes

liked a model 10 months ago

microsoft/Phi-4-multimodal-instruct

Automatic Speech Recognition • 6B • Updated 17 days ago • 284k • 1.55k

upvoted an article 10 months ago