leeky

leeky - training data contamination techniques for blackbox models

MIT License

Stars

Ecosystems: Python

Statistics for this project are still being loaded, please check back later.

This repository recorded my NLP journey.

Multilingual Semantic Search with Reranking on a prepared large vectorized dataset comprising 10 ...

The guide to tackle with the Text Summarization

An accessible, reliable, and efficient platform for medical information and support using LLMs

Chat language model that can use tools and interpret the results

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critiqu...

Document Search Engine project with TF-IDF abd Google universal sentence encoder model

Keyphrase Generation for Scientific Document Retrieval

ktrain is a Python library that makes deep learning and AI more accessible and easier to apply

Python API & command-line tool to easily transcribe speech-based video files into clean text

Reading Wikipedia to Answer Open-Domain Questions

A collection of datasets and tasks for legal machine learning