Samuel Lima Braz's picture

Samuel Lima Braz

samuellimabraz

·

https://samuellimabraz.github.io/

AI & ML interests

None yet

Organizations

upvoted a collection 21 days ago

SmolVLM GGUF

6 items • Updated May 14 • 4

upvoted an article 22 days ago

Article

SmolLM3: smol, multilingual, long-context reasoner

By

and 22 others •

23 days ago

• 598

upvoted 2 articles about 2 months ago

Article

KV Cache from scratch in nanoVLM

By

and 4 others •

Jun 4

• 88

Article

Accelerating Document AI

By

and 3 others •

Nov 21, 2022

• 71

upvoted an article 3 months ago

Article

Vision Language Models (Better, Faster, Stronger)

By

and 4 others •

May 12

• 491

upvoted a collection 3 months ago

D-FINE

State-of-the-art real-time object detection model with Apache 2.0 licence • 15 items • Updated May 5 • 55

upvoted 2 articles 3 months ago

Article

The NLP Course is becoming the LLM Course!

By

and 9 others •

Apr 3

• 98

Article

Welcoming Llama Guard 4 on Hugging Face Hub

By

and 3 others •

Apr 29

• 40

upvoted a paper 4 months ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7 • 196

upvoted 2 collections 4 months ago

Portuguese LLM Leaderboard best models ❤️‍🔥

A daily uploaded list of models with best evaluations on the PT-LLM leaderboard: • 17 items • Updated 41 minutes ago • 36

H2OVL Mississippi

H2O Multimodal models • 9 items • Updated Feb 20 • 7

upvoted an article 4 months ago

Article

π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

By

and 3 others •

Feb 4

• 167

upvoted a paper 4 months ago

GuardReasoner: Towards Reasoning-based LLM Safeguards

Paper • 2501.18492 • Published Jan 30 • 88

upvoted an article 5 months ago

Article

Open-Source Handwritten Signature Detection Model

By

•

Mar 14

• 114

upvoted 2 articles 6 months ago

Article

Vision Language Models Explained

By

and 1 other •

Apr 11, 2024

• 422

Article

Open-source DeepResearch – Freeing our search agents

By

and 4 others •

Feb 4

• 1.28k

upvoted a collection 6 months ago

ViTucano-v1

ViTucano is our first attempt at creating a vision assistant natively pretrained in Portuguese. ViTucano is built on top of the Tucano series. • 5 items • Updated May 31 • 1

upvoted 3 articles 6 months ago

Article

Mastering Tensor Dimensions in Transformers

By

•

Jan 12

• 79

Article

KV Caching Explained: Optimizing Transformer Inference Efficiency

By

•

Jan 30

• 105

Article

PEFT: Parameter-Efficient Fine-Tuning Methods for LLMs

By

•

Jan 24

• 32