tiktoken is a fast BPE tokeniser for use with OpenAI's models.

YSDA course in Natural Language Processing

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

A framework for prompt tuning using Intent-based Prompt Calibration

Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

A Python package for causal inference in quasi-experimental settings

Metric learning and retrieval pipelines, models and zoo.

MSc Thesis on evolvement of music diversity in the era of rising dominance of DSPs. It is based on a Big Data comparative content analysis of national music charts enriched with Spotify track metad…

Some useful tips for faiss

Topic Modelling for Humans

Fast numerical array expression evaluator for Python, NumPy, Pandas, PyTables and more

Fast and customizable framework for automatic and quick Causal Inference in Python

RecTools - library to build Recommendation Systems easier and faster than ever before

ETNA – Time-Series Library

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports comp…

Ambrosia is a Python library for A/B tests design, split and result measurement

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

ETNA – Time-Series Library

Extra blocks for scikit-learn pipelines.

Home assignments for data science positions

This library is for simplified work with the sms-man.com API

3rd place solution for RetailHero.ai/#2