rennancl

langchain

🦜🔗 Build context-aware reasoning applications

CasaOS

CasaOS - A simple, easy-to-use, elegant open-source Personal Cloud system.

crawlee

Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.

trl

Train transformer language models with reinforcement learning.

xv6-public

xv6 OS

chat-ui

Open source codebase powering the HuggingChat app

xv6-riscv

Xv6 for RISC-V

orjson

Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

torchtune

A Native-PyTorch Library for LLM Fine-tuning

long_llama

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

summarize-from-feedback

Code for "Learning to summarize from human feedback"

cabrita

Finetuning InstructLLaMA with portuguese data

GoogleSearchCrawler

a tool for crawl Google search results

MLE-LLaMA

Multi-language Enhanced LLaMA

factCC

Resources for the "Evaluating the Factual Consistency of Abstractive Text Summarization" paper

hiersumm

Code for paper Hierarchical Transformers for Multi-Document Summarization in ACL2019

llama2_local

CAMEL

Clinically Adapted Model Enhanced from LLaMA

LongDocSum

Code for NAACL 2021 full paper "Efficient Attentions for Long Document Summarization"

tabsyn

Official Implementations of "Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space""

colberter

pesquisas-presidenciais-2022

Pesquisas para presidente - 2022

summary-reference-revision

C01

Coleta de Dados Públicos

graphingPhilosophy

ppgccufmg

Uma classe LaTeX para dissertações, teses e propostas do Programa de Pós-Graduação em Ciência da Computação (PPGCC) da Universidade Federal de Minas Gerais (UFMG).

QueCos_code

The code repo for <Enriching Query Semantics for Code Search with Reinforcement Learning>

KorKeyBLD_NLP

Effective Retrieval Model implementing "KeyBLD : Selecting Key Blocks with Pre-ranking for Long Document Information Retrieval" with Korean dataset.

abusive-language

Code for the paper "On the Presence of Abusive Language in Mis/Disinformation", accepted at SocInfo 2022.