An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

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

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

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

Python library for knowledge graph embedding and representation learning.

Source code of MetaP

reimplement TransE Mode

[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

🤖 A Python library for learning and evaluating knowledge graph embeddings

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

An Open-Source Package for Knowledge Embedding (KE)

[ACL 2022] Transformers for Input Method Engine

汉字转拼音(pypinyin)

Code for ACL 2021 paper "ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information"

Resources and code for paper "Multiplingual Knowledge Graph Completion via Ensemble Knowledge Transfer"

A collection of research on knowledge graphs

OpenCC made with Python

Code repo for ACL22 paper "DeepStruct: Pretraining of Language Models for Structure Prediction"

An industrial-grade implementation of DSSM

Noah Research

Chinese Open Information Extraction (Tree-based Triple Relation Extraction Module)

Code for One-shot Relational Learning for Knowledge Graphs (EMNLP18)

Code repo for EMNLP21 paper "Zero-Shot Information Extraction as a Unified Text-to-Triple Translation"