Code and documentation to train Stanford's Alpaca models, and generate the data.

Aligning pretrained language models with instruction data generated by themselves.

Running large language models like OPT-175B/GPT-3 on a single GPU. Focusing on high-throughput large-batch generation.

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

Making big AI models cheaper, easier, and scalable

Reverse engineered ChatGPT API

使用ChatGPT搭建微信聊天机器人，基于OpenAI API和itchat实现。Wechat robot based on ChatGPT, which using OpenAI api and itchat library.

Code for the paper "Language Models are Unsupervised Multitask Learners"

Lbl2Vec learns jointly embedded label, document and word vectors to retrieve documents with predefined topics from an unlabeled document corpus.

An Open Toolkit for Knowledge Graph Extraction and Construction published at EMNLP2022 System Demonstrations

[NeurIPS 2020] "Graph Contrastive Learning with Augmentations" by Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang Shen

AMD, Intel and NVIDIA GPUs process monitoring

Cloud-native Deep Reinforcement Learning. 🔥

Source code for AAAI 2022 paper: Unified Named Entity Recognition as Word-Word Relation Classification

code for EMNLP 2019 paper Text Summarization with Pretrained Encoders

An original implementation of "MetaICL Learning to Learn In Context" by Sewon Min, Mike Lewis, Luke Zettlemoyer and Hannaneh Hajishirzi

[ACL 2022] LinkBERT: A Knowledgeable Language Model 😎 Pretrained with Document Links

Collections of vector search related libraries, service and research papers

An Open-Source Framework for Prompt-Learning.

EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings

Implementation and experiments of graph neural netwokrs, like gcn,graphsage,gat,etc.

This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

Fine-grained Post-training for Improving Retrieval-based Dialogue Systems - NAACL 2021

This project provides an unsupervised framework for mining and tagging quality phrases on text corpora with pretrained language models (KDD'21).

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

Automated Phrase Mining from Massive Text Corpora in Python.