Modeling, training, eval, and inference code for OLMo

Unify Efficient Fine-Tuning of 100+ LLMs

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.

gpt4all: a chatbot trained on a massive collection of clean assistant data including code, stories and dialogue

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

Datasets, SOTA results of every fields of Chinese NLP

Easy OpenAPI specs and Swagger UI for your Flask API

对ACL2020 FastBERT论文的复现，论文地址:https://arxiv.org/pdf/2004.02178.pdf

Stanford Open Information Extraction made simple!

Multilingual Sentence & Image Embeddings with BERT

Examples and guides for using the OpenAI API

Learn OpenCV : C++ and Python Examples

😎 Awesome list of tools and projects with the awesome LangChain framework

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

用 Express 和 Vue3 搭建的 ChatGPT 演示网页

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

Repo for external large-scale work

An open-source vector database for scalable similarity search and AI applications.

Language Technology Platform

✨Fast Coreference Resolution in spaCy with Neural Networks

Documentations for PaddlePaddle

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

💫 Models for the spaCy Natural Language Processing (NLP) library

Entity and Relation Extraction Based on TensorFlow and BERT. 基于TensorFlow和BERT的管道式实体及关系抽取，2019语言与智能技术竞赛信息抽取任务解决方案。Schema based Knowledge Extraction, SKE 2019

A very simple framework for state-of-the-art Natural Language Processing (NLP)

Unsupervised Data Augmentation (UDA)