Pinned Repositories
ir-utils
Gaggle of information retrieval codes I found myself re-writing constantly
rerankers
t5-deep-ocr-extractor
Scanned receipts information extraction with Google Vision and T5 models
PTT5
Code for training and evaluating T5 on Portuguese data.
marcospiau's Repositories
marcospiau/rerankers
marcospiau/awk-hack-the-planet
Source code repo for Ben Porter (FreedomBen)'s talk at Linux Fest Northwest 2019 and 2020
marcospiau/BankMarketingDataSet
marcospiau/bm25-cisi
marcospiau/ir-utils
Gaggle of information retrieval codes I found myself re-writing constantly
marcospiau/t5-deep-ocr-extractor
Scanned receipts information extraction with Google Vision and T5 models
marcospiau/batchwizard
A CLI tool for managing OpenAI batch processing jobs with ease.
marcospiau/boruta_py
Python implementations of the Boruta all-relevant feature selection method.
marcospiau/ColBERT-pt
ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22)
marcospiau/curso_audio
Curso introdutório (e interativo) de análise e síntese de áudio usando iPython Notebook e sklearn.
marcospiau/datasets
TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
marcospiau/dotfiles
marcospiau/Dynamic-Risk-Assessment-System
The fourth project in the Machine Learning DevOps Nanodegree by Udacity.
marcospiau/EE641_lab_eletronica2
Laboratório de eletrônica 2 - 2s2016 - Turma P
marcospiau/gpt-neo
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
marcospiau/ia368-dd-dl4ir
marcospiau/mesh
Mesh TensorFlow: Model Parallelism Made Easier
marcospiau/ml-devops-eng-nanodegree-churn-prediction
marcospiau/ml-devops-nanodegree-project-course-4
Final project for fourth course of Udacity's MLOPS Nanodegree "4. Deploying a Scalable ML Pipeline in Production"
marcospiau/nd0821-c2-build-model-workflow-exercises
Exercise Code for Course 2 of the Udacity ML DevOps Nanodegree Program
marcospiau/nd0821-c2-build-model-workflow-starter
Starter Code for the Course 2 project of the Udacity ML DevOps Nanodegree Program
marcospiau/PTT5
Repository for training T5 to portuguese.
marcospiau/pylate
Late Interaction Models Training & Retrieval
marcospiau/pytrends
Pseudo API for Google Trends
marcospiau/titanic-kaggle
Estudos usando a competição "Titanic: Machine Learning from Disaster" do Kaggle