Elias Jacob's Projects
Repository containing code for "How to Train BERT with an Academic Budget" paper
Generating Training Data Made Easy
A curated list of programmatic weak supervision papers and resources
review dataset
architectures and pre-trained models for long document classification.
Code for the Book Causal Inference in Python
Code For Medium Article: "How To Create Natural Language Semantic Search for Arbitrary Objects With Deep Learning"
[NAACL 2021] This is the code for our paper `Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach'.
Resources for Data Centric AI
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
Deep Learning experiments
Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101
Example Repo for the Udemy Course "Deployment of Machine Learning Models"
Protótipo submetido pela equipe 22 do desafio CNJ/ENAP
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
The fastai deep learning library, plus lessons and tutorials
Scrapes posts and comments from public Facebook pages.
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Build large language model (LLM) apps with Python, ChatGPT and other models. This is the companion repository for the book on generative AI with LangChain.
Final exerciseof the Udacity class on Machine Learning workflows
Generalist model for NER (Extract any entity types from texts)
INSPIRE text classification microservice
Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling
Jupyter notebook for interactive weak supervision ODSC Europe talk
An ongoing list of pandas quirks
🦜⛏️ Did you say you like data?
pre-trained Language Models
Source code and checkpoints for legal pre-trained language models.