Nikolay Karelin (karelin)

karelin

Geek Repo

Company:SilkData.ai

Github PK Tool:Github PK Tool

Nikolay Karelin's starred repositories

Flowise

Drag & drop UI to build your customized LLM flow

Language:TypeScriptLicense:Apache-2.0Stargazers:26391Issues:217Issues:1061

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Language:PythonLicense:MITStargazers:8516Issues:79Issues:34

llm-answer-engine

Build a Perplexity-Inspired Answer Engine Using Next.js, Groq, Llama-3, Langchain, OpenAI, Upstash, Brave & Serper

Language:TypeScriptLicense:MITStargazers:4161Issues:45Issues:43

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

Language:PythonLicense:MITStargazers:2979Issues:30Issues:85

tidy-text-mining

Manuscript of the book "Tidy Text Mining with R" by Julia Silge and David Robinson

Language:TeXLicense:NOASSERTIONStargazers:1305Issues:135Issues:69

rebuff

LLM Prompt Injection Detector

Language:TypeScriptLicense:Apache-2.0Stargazers:968Issues:14Issues:55

langkit

🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:750Issues:14Issues:54

MobiLlama

MobiLlama : Small Language Model tailored for edge devices

Language:PythonLicense:Apache-2.0Stargazers:551Issues:13Issues:12

Complete-Machine-Learning-

This repository contains everything you need to become proficient in Machine Learning

License:MITStargazers:454Issues:11Issues:0

text-clustering

Easily embed, cluster and semantically label text datasets

Language:PythonLicense:Apache-2.0Stargazers:367Issues:35Issues:5

PassportEye

Extraction of machine-readable zone information from passports, visas and id-cards via OCR

Language:PythonLicense:MITStargazers:366Issues:20Issues:62

galactic

data cleaning and curation for unstructured text

Language:PythonLicense:Apache-2.0Stargazers:316Issues:8Issues:4

super-rag

Super performant RAG pipelines for AI apps. Summarization, Retrieve/Rerank and Code Interpreters in one simple API.

Language:PythonLicense:MITStargazers:301Issues:6Issues:49

smltar

Manuscript of the book "Supervised Machine Learning for Text Analysis in R" by Emil Hvitfeldt and Julia Silge

Language:TeXLicense:NOASSERTIONStargazers:245Issues:15Issues:163

chat-with-websites

Latests Langchain (2024) App to chat with any website given its URL

amber-train

Pre-training code for Amber 7B LLM

Language:PythonLicense:Apache-2.0Stargazers:139Issues:8Issues:5

ghostbuster

Ghostbuster: Detecting Text Ghostwritten by Large Language Models (NAACL 2024)

Language:PythonLicense:NOASSERTIONStargazers:121Issues:3Issues:7

logot

Test whether your code is logging correctly 🪵

Language:PythonLicense:MITStargazers:95Issues:2Issues:19

realtime-indexer-qa-chat

Streamlit app providing real-time question-answering chat over a document collection.

Language:DockerfileLicense:MITStargazers:90Issues:5Issues:0

dl-hse-ami

Deep Learning course materials (HSE, Faculty of Computer Science)

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:35Issues:3Issues:0

homeai

AI real estate agent

ds_interview_prep_resources

Comprehensive resources for data science interview preparation: assignments, math problems, logic tasks, live coding examples, and leetcode breakdowns.

Language:Jupyter NotebookStargazers:24Issues:2Issues:1
Language:PythonLicense:NOASSERTIONStargazers:22Issues:2Issues:0

luigi-course-materials

Материалы для курса Введение в Data Engineering: дата пайплайны

Language:PythonStargazers:12Issues:4Issues:0

yongks-python-rmarkdown-book

A Python book written in Rmarkdown. Author yongks

Language:HTMLLicense:CC0-1.0Stargazers:9Issues:1Issues:0

kingsbounty3

King's Bounty 3 (extended JavaScript fan remake of original 1990 game)

Language:JavaScriptLicense:MITStargazers:8Issues:0Issues:0
Language:PythonLicense:MITStargazers:5Issues:0Issues:0

ghostbuster-data

Data from the paper "Ghostbuster: Detecting Text Ghostwritten by Large Language Models"

License:NOASSERTIONStargazers:5Issues:0Issues:0
Language:MakefileStargazers:3Issues:0Issues:0

book

An Introduction to Quantitative Text Analysis for Linguistics: Reproducible Research using R