Code for CPM-2 Pre-Train

Last update: Dec 28, 2022

Related tags

Deep Learning CPM-2

Overview

CPM-2 Pre-Train

Pre-train CPM-2 此分支为110亿非 MoE 模型的预训练代码，MoE 模型的预训练代码请切换到 moe 分支

CPM-2技术报告请参考link。

0 模型下载

请在智源资源下载页面进行申请，文件介绍如下：

文件名	描述	参数大小
100000.tar	纯中文模型	110亿
36000.tar	中英文双语模型	110亿
300000.tar	中英文MoE模型	1980亿

1 安装

可以直接拉取我们提供的 Docker 环境：

docker pull gyxthu17/cpm-2:1.0

2 数据

scripts/gen_data.sh 中给出了生成数据文件的脚本示例。该脚本将一个多行的纯文本文件（一个 document 一行）转化为二进制文件（会输出三个 .bin 和三个 .idx 文件），方便模型读取。

3 训练

首先需要将 WORKING_DIR 变量换成 CPM-2 目录的所在路径。调整 NUM_WORKERS 和 NUM_GPUS_PER_WORKER 指定机器数量与每台机器的 GPU 设备数量。修改 ${WORKING_DIR}/src/configs/host_files/hostfile-cpm2 文件将其中的主机名称替换成每台机器的 IP 地址或者和 IP 地址相关联的主机名称。

运行命令：

cd src
bash scripts/pretrain_enc_dec.sh

4 引用

如果您使用了我们的代码，请您引用下面的文章。

@article{cpm-v2,
  title={CPM-2: Large-scale Cost-efficient Pre-trained Language Models},
  author={Zhang, Zhengyan and Gu, Yuxian and Han, Xu and Chen, Shengqi and Xiao, Chaojun and Sun, Zhenbo and Yao, Yuan and Qi, Fanchao and Guan, Jian and Ke, Pei and Cai, Yanzheng and Zeng, Guoyang and Tan, Zhixing and Liu, Zhiyuan and Huang, Minlie and Han, Wentao and Liu, Yang and Zhu, Xiaoyan and Sun, Maosong},
  year={2021}
}

Code for CPM-2 Pre-Train

Related tags

Overview

CPM-2 Pre-Train

0 模型下载

1 安装

2 数据

3 训练

4 引用

Owner

Tsinghua AI

Code for LIGA-Stereo Detector, ICCV'21

Spherical Confidence Learning for Face Recognition, accepted to CVPR2021.

The AWS Certified SysOps Administrator

OoD Minimum Anomaly Score GAN - Code for the Paper 'OMASGAN: Out-of-Distribution Minimum Anomaly Score GAN for Sample Generation on the Boundary'

Code for paper ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop.

Using some basic methods to show linkages and transformations of robotic arms

K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce (EMNLP Founding 2021)

Implementation of Wasserstein adversarial attacks.

An unofficial styleguide and best practices summary for PyTorch

This repository contains the code for "Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP".

Our VMAgent is a platform for exploiting Reinforcement Learning (RL) on Virtual Machine (VM) scheduling tasks.

This implements one of result networks from Large-scale evolution of image classifiers

Official Repo for Ground-aware Monocular 3D Object Detection for Autonomous Driving

LyaNet: A Lyapunov Framework for Training Neural ODEs

The MATH Dataset

Practical tutorials and labs for TensorFlow used by Nvidia, FFN, CNN, RNN, Kaggle, AE

A fast Evolution Strategy implementation in Python

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

Convert Python 3 code to CUDA code.