leofn

gpt4all

GPT4All: Chat with Local LLMs on Any Device

faiss

A library for efficient similarity search and clustering of dense vectors.

ML-YouTube-Courses

📺 Discover the latest machine learning / AI courses on YouTube.

Transformers-Tutorials

This repository contains demos I made with the Transformers library by HuggingFace.

BrasilAPI

Vamos transformar o Brasil em uma API?

ML-Course-Notes

🎓 Sharing machine learning course / lecture notes.

venom

Venom is a high-performance system developed with JavaScript to create a bot for WhatsApp, support for creating any interaction, such as customer service, media sending, sentence recognition based on artificial intelligence and all types of design architecture for WhatsApp.

free-livros

Educação é um direito de todos

chart-doctor

Sample files to accompany the FT's Chart Doctor column

Top2Vec

Top2Vec learns jointly embedded topic, document and word vectors.

pytextrank

Python implementation of TextRank algorithms ("textgraphs") for phrase extraction

setfit

Efficient few-shot learning with Sentence Transformers

portuguese-bert

Portuguese pre-trained BERT models

cabrita

Finetuning InstructLLaMA with portuguese data

awesome-computational-social-science

A list of awesome resources for Computational Social Science

BetterOCR

🔍 Better text detection by combining multiple OCR engines (EasyOCR, Tesseract, and Pororo) with 🧠 LLM.

portuguese_word_embeddings

Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks

hate-speech-dataset

Hate speech dataset from Stormfront forum manually labelled at sentence level.

FaceCut

tjsp

Baixa processos e decisões do Tribunal de Justiça de São Paulo

dh-r

Computational Historical Thinking: With Applications in R

workshop_big_data_conference

Workshop "Analyzing Social Media Data" at the Big Data and Development Conference

projeto-dou

br-elections-on-twitter

Using data from twitter to create analyses about Brazilian Elections

rotas

Análise de Dados (rotas.csv) realizando: agrupamento, classificação, predição, otimização e recomendação.

PontuarLattes

Tabelas com pontuação Qualis a partir do Lattes

codelab22_1

Repositório com os dados das sessões do CodeLab do IESP-UERJ, realizado em 2022.1, liderado por Luana Calzavara e Matheus Pestana.

darkplatforms

Collection of corpora compiled from so-called "dark" platforms

ex-agents-langchain

NFETC

Neural Fine-grained Entity Type Classification https://arxiv.org/abs/1803.03378