🔍 LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

Module for automatic summarization of text documents and HTML pages.

Python implementation of TextRank algorithms ("textgraphs") for phrase extraction

A modular RL library to fine-tune language models to human preferences

Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0

Returns latest research results by crawling arxiv papers and summarizing abstracts. Helps you stay afloat with so many new papers everyday.

TextRank implementation for Python 3.

Summarization Papers

Efficient Retrieval Augmentation and Generation Framework

pytorch implementation of "Get To The Point: Summarization with Pointer-Generator Networks"

Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

Transformers 库快速入门教程

Converse with book - Built with GPT-3

Basic statistics for Julia

Automatically generate headlines to short articles

Korean BART

Models to perform neural summarization (extractive and abstractive) using machine learning transformers and a tool to convert abstractive summarization datasets to the extractive task.

Abstractive summarisation using Bert as encoder and Transformer Decoder

simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.

Pointer-generator reinforced seq2seq summarization in PyTorch