Code for CPM-2 Pre-Train

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_WORKERSNUM_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}
}
Owner
Tsinghua AI
Tsinghua AI
Retrieval.pytorch - The code we used in [2020 DIGIX]

Retrieval.pytorch - The code we used in [2020 DIGIX]

Guo-Hua Wang 2 Feb 07, 2022
(CVPR2021) ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic

ClassSR (CVPR2021) ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic Paper Authors: Xiangtao Kong, Hengyuan

Xiangtao Kong 308 Jan 05, 2023
PyTorch implementation of "Optimization Planning for 3D ConvNets"

Optimization-Planning-for-3D-ConvNets Code for the ICML 2021 paper: Optimization Planning for 3D ConvNets. Authors: Zhaofan Qiu, Ting Yao, Chong-Wah N

Zhaofan Qiu 2 Jan 12, 2022
Cross Quality LFW: A database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments

Cross-Quality Labeled Faces in the Wild (XQLFW) Here, we release the database, evaluation protocol and code for the following paper: Cross Quality LFW

Martin Knoche 10 Dec 12, 2022
Background Matting: The World is Your Green Screen

Background Matting: The World is Your Green Screen By Soumyadip Sengupta, Vivek Jayaram, Brian Curless, Steve Seitz, and Ira Kemelmacher-Shlizerman Th

Soumyadip Sengupta 4.6k Jan 04, 2023
The implementation of our CIKM 2021 paper titled as: "Cross-Market Product Recommendation"

FOREC: A Cross-Market Recommendation System This repository provides the implementation of our CIKM 2021 paper titled as "Cross-Market Product Recomme

Hamed Bonab 16 Sep 12, 2022
Code release for "MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound"

merlot_reserve Code release for "MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound" MERLOT Reserve (in submission) is a mo

Rowan Zellers 92 Dec 11, 2022
git《Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser》(2021) GitHub: [fig5]

Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser Abstract The success of deep denoisers on real-world colo

Yue Cao 51 Nov 22, 2022
An Efficient Training Approach for Very Large Scale Face Recognition or F²C for simplicity.

Fast Face Classification (F²C) This is the code of our paper An Efficient Training Approach for Very Large Scale Face Recognition or F²C for simplicit

33 Jun 27, 2021
Multiview 3D object detection on MultiviewC dataset through moft3d.

Multiview Orthographic Feature Transformation for 3D Object Detection Multiview 3D object detection on MultiviewC dataset through moft3d. Introduction

Jiahao Ma 20 Dec 21, 2022
A PyTorch Implementation of Gated Graph Sequence Neural Networks (GGNN)

A PyTorch Implementation of GGNN This is a PyTorch implementation of the Gated Graph Sequence Neural Networks (GGNN) as described in the paper Gated G

Ching-Yao Chuang 427 Dec 13, 2022
DeepSTD: Mining Spatio-temporal Disturbances of Multiple Context Factors for Citywide Traffic Flow Prediction

DeepSTD: Mining Spatio-temporal Disturbances of Multiple Context Factors for Citywide Traffic Flow Prediction This is the implementation of DeepSTD in

5 Sep 26, 2022
mbrl-lib is a toolbox for facilitating development of Model-Based Reinforcement Learning algorithms.

mbrl-lib is a toolbox for facilitating development of Model-Based Reinforcement Learning algorithms. It provides easily interchangeable modeling and planning components, and a set of utility function

Facebook Research 724 Jan 04, 2023
This repository contains various models targetting multimodal representation learning, multimodal fusion for downstream tasks such as multimodal sentiment analysis.

Multimodal Deep Learning 🎆 🎆 🎆 Announcing the multimodal deep learning repository that contains implementation of various deep learning-based model

Deep Cognition and Language Research (DeCLaRe) Lab 398 Dec 30, 2022
Users can free try their models on SIDD dataset based on this code

SIDD benchmark 1 Train python train.py If you want to train your network, just modify the yaml in the options folder. 2 Validation python validation.p

Yuzhi ZHAO 2 May 20, 2022
SatelliteSfM - A library for solving the satellite structure from motion problem

Satellite Structure from Motion Maintained by Kai Zhang. Overview This is a libr

Kai Zhang 190 Dec 08, 2022
RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

184 Jan 04, 2023
Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement

Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement In this project, we proposed a Domain Disentanglement Faster-RCNN (DDF)

19 Nov 24, 2022
Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight

PCAN for Multiple Object Tracking and Segmentation This is the offical implementation of paper PCAN for MOTS. We also present a trailer that consists

ETH VIS Group 328 Dec 29, 2022
🔪 Elimination based Lightweight Neural Net with Pretrained Weights

ELimNet ELimNet: Eliminating Layers in a Neural Network Pretrained with Large Dataset for Downstream Task Removed top layers from pretrained Efficient

snoop2head 4 Jul 12, 2022