Marcus Pop (MarcusGitAccount)

MarcusGitAccount

Geek Repo

Location:Cluj-Napoca, Romania

Github PK Tool:Github PK Tool

Marcus Pop's starred repositories

langchain

🦜🔗 Build context-aware reasoning applications

Language:Jupyter NotebookLicense:MITStargazers:91146Issues:678Issues:7440

llama.cpp

LLM inference in C/C++

llama

Inference code for Llama models

Language:PythonLicense:NOASSERTIONStargazers:55202Issues:517Issues:953

whisper.cpp

Port of OpenAI's Whisper model in C/C++

poetry

Python packaging and dependency management made easy

Language:PythonLicense:MITStargazers:30886Issues:191Issues:5829

nylas-mail

:love_letter: An extensible desktop mail app built on the modern web. Forks welcome!

Language:JavaScriptLicense:MITStargazers:24809Issues:463Issues:3422

DVWA

Damn Vulnerable Web Application (DVWA)

Language:PHPLicense:GPL-3.0Stargazers:9891Issues:308Issues:430

HackMyResume

Generate polished résumés and CVs in HTML, Markdown, LaTeX, MS Word, PDF, plain text, JSON, XML, YAML, smoke signal, and carrier pigeon.

Language:JavaScriptLicense:MITStargazers:9266Issues:204Issues:171

petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

Language:PythonLicense:MITStargazers:9035Issues:90Issues:199

yugabyte-db

YugabyteDB - the cloud native distributed SQL database for mission-critical applications.

Language:CLicense:NOASSERTIONStargazers:8738Issues:248Issues:19224

prompt-engineering

Tips and tricks for working with Large Language Models like OpenAI's GPT-4.

unstructured

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Language:HTMLLicense:Apache-2.0Stargazers:8150Issues:52Issues:1102

langchain-tutorials

Overview and tutorial of the LangChain Library

Language:Jupyter NotebookStargazers:6611Issues:107Issues:36

learn-cantrill-io-labs

Standard and Advanced Demos for learn.cantrill.io courses

Language:PythonLicense:MITStargazers:5500Issues:322Issues:45

openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

Language:PythonLicense:Apache-2.0Stargazers:5188Issues:50Issues:187

ann-benchmarks

Benchmarks of approximate nearest neighbor libraries in Python

Language:PythonLicense:MITStargazers:4824Issues:117Issues:206

mljar-supervised

Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation

Language:PythonLicense:MITStargazers:2991Issues:50Issues:650

PySR

High-Performance Symbolic Regression in Python and Julia

Language:PythonLicense:Apache-2.0Stargazers:2162Issues:28Issues:229

etl-with-airflow

ETL best practices with airflow, with examples

textstat

:memo: python package to calculate readability statistics of a text object - paragraphs, sentences, articles.

Language:PythonLicense:MITStargazers:1121Issues:19Issues:112

awesome-instruction-dataset

A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

content-moderation-deep-learning

Deep learning based content moderation from text, audio, video & image input modalities.

License:MITStargazers:301Issues:5Issues:0

GenRead

Code and Checkpoints for "Generate rather than Retrieve: Large Language Models are Strong Context Generators" in ICLR 2023.

RecAlign

Chrome extension to filter your feed with LLM according to an explicitly stated and user-editable preference.

Language:TypeScriptLicense:MITStargazers:253Issues:6Issues:3

Romanian-Transformers

This repo is the home of Romanian Transformers.

ronec

Romanian Named Entity Corpus (RONEC) version 2.0

Language:PythonLicense:MITStargazers:60Issues:9Issues:6

Polygon-Partition

Python code for partitioning rectilinear polygon in O(n) time complexity

Language:Jupyter NotebookStargazers:40Issues:1Issues:1

Romanian-NLP-tools

A list of Natural Language Processing Tools for Romanian

Language:Jupyter NotebookLicense:MITStargazers:16Issues:3Issues:0

wiki-ro

Romanian Wikipedia dump that is cleaned and pre-processed, for language model capacity and perplexity evaluation.