Stars
ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.
AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/pAbnFJrkgZ
🔋 Next.js + Tailwind CSS + TypeScript starter and boilerplate packed with useful development features
Clean Architecture Example using FastAPI framework
Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.
Instruct-tune LLaMA on consumer hardware
A playbook for systematically maximizing the performance of deep learning models.
Portuguese pre-trained BERT models
Fit Sparse Synthetic Control Models in Python
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…
Template for a data science project
Uplift modeling and causal inference with machine learning algorithms
Behavioral "black-box" testing for recommender systems
An end-to-end implementation of intent prediction with Metaflow and other cool tools
Production infrastructure for machine learning at scale
The fastai book, published as Jupyter Notebooks
Faker is a Python package that generates fake data for you.
TensorFlow code and pre-trained models for BERT
Source code for the CORVIDS data reconstruction system
aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)
Real-time stream processing for python
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive lea…
BayesDB on SQLite. A Bayesian database table for querying the probable implications of data as easily as SQL databases query the data itself.