dkajtoch

glove_streamlit

Demonstration project of using Streamlit with word embeddings.

Boson-Gutzwiller

Ground state of the Gutzwiller wavefunction for one- and two-component Bose-Hubbard model

fast-lang

Language detection tool based on fastText pretrained model.

adaptive-inertia-adai

The PyTorch Implementation of Adaptive Inertia Methods. The algorithms are based on our ICML2020 Long Oral paper: "Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum".

awesome-nlp-polish

A curated list of resources dedicated to Natural Language Processing (NLP) in polish. Models, tools, datasets.

Data-Science-Projects

Collection of Data Science Projects

datasets

🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools

embeddings

Embeddings: State-of-the-art Text Representations for Natural Language Processing tasks, an initial version of library focus on the Polish Language

guidance

A guidance language for controlling large language models.

LEPISZCZE

This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish

LinuxConfigurationFiles

Personal configuration files

Machine-Learning-Tutorials

Personal material on Machine Learning

dkajtoch.github.io

langchain

⚡ Building applications with LLMs through composability ⚡

matplotblog

Matplotlib blog

ml

paws

This dataset contains 108,463 human-labeled and 656k noisily labeled pairs that feature the importance of modeling structure, context, and word order information for the problem of paraphrase identification.

pipelines

Machine Learning Pipelines for Kubeflow

pytorch-lightning

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

pytorch-lightning-gcp-project-template

Repository template for pytorch-lightning based projects run on GCP

pytorch-optimizer

torch-optimizer -- collection of optimizers for Pytorch

scrapy-exception-bypass

Temporary fix to limited functionality of Scrapy Downloader

scrapy-redirect

Scrapy redirect middleware

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

setfit

Efficient few-shot learning with Sentence Transformers

StrangeAttractor

Generate images of strange attractor

text

Data loaders and abstractions for text and NLP

torchx

TorchX is a universal job launcher for PyTorch applications. TorchX is designed to have fast iteration time for training/research and support for E2E production ML pipelines when you're ready.

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

w3lib

Python library of web-related functions