🙌 OpenHands: Code Less, Make More

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Get your documents ready for gen AI

An AI Hedge Fund Team

An open-source RAG-based tool for chatting with your documents.

Train transformer language models with reinforcement learning.

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

The Data Engineering Cookbook

Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

Model summary in PyTorch similar to `model.summary()` in Keras

AdalFlow: The library to build & auto-optimize LLM applications.

Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

基于知识图谱的问答系统，BERT做命名实体识别和句子相似度，分为online和outline模式

Tutorial: Graph Neural Networks for Natural Language Processing at EMNLP 2019 and CODS-COMAD 2020

[ACL 2021] LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723

GIPHY's Open-Source Celebrity Detection Deep Learning Model

AI Travel Agent

AutoPrompt: Automatic Prompt Construction for Masked Language Models.

BERT models for Japanese text.

im2recipe Pytorch implementation

A scalable & efficient active learning/data selection system for everyone.

A solution guidance for Generative BI using Amazon Bedrock, Amazon OpenSearch with RAG

Transformer for abstractive summarization on cnn/daily-mail and gigawords

Gradient Reversal Layer for Domain Adaptation

langchain-chat is an AI-driven Q&A system that leverages OpenAI's GPT-4 model and FAISS for efficient document indexing. It loads and splits documents from websites or PDFs, remembers conversations…

Implementation of Sequence to Sequence Learning with Neural Networks by Sutskever et al.