Use PaddlePaddle to reproduce the paper:mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer

Overview

MT5_paddle

Use PaddlePaddle to reproduce the paper:mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer

English | 简体中文

mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer

Abstract: The recent “Text-to-Text Transfer Transformer” (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks. In this paper, we introduce mT5, a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset covering 101 languages. We detail the design and modified training of mT5 and demonstrate its state-of-the-art performance on many multilingual benchmarks. We also describe a simple technique to prevent “accidental translation” in the zero-shot setting, where a generative model chooses to (partially) translate its prediction into the wrong language. All of the code and model checkpoints used in this work are publicly available.

This project is an open source implementation of MT5 on Paddle 2.x.

Environment Installation

label value
python >=3.6
GPU V100
Frame PaddlePaddle2.1.2
Cuda 10.1
Cudnn 7.6

Cloud platform used in this recurrence:https://aistudio.baidu.com/

# Clone the repository
git clone https://github.com/27182812/MT5_paddle
# Enter the root directory
cd MT5_paddle
# Install the necessary python libraries locally
pip install -r requirements.txt

"test.ipynb" has run results display.

Quick Start

(一)Tokenizer Accuracy Alignment

### 对齐tokenizer
text = "Welcome to use paddle and paddlenlp!"
torch_tokenizer = PTT5Tokenizer.from_pretrained("./mt5-large")
paddle_tokenizer = PDT5Tokenizer.from_pretrained("./mt5-large")
torch_inputs = torch_tokenizer(text)
paddle_inputs = paddle_tokenizer(text)
print(torch_inputs)
print(paddle_inputs)

(二)Model Accuracy Alignment

run python compare.py,Comparing the accuracy between huggingface and paddle.

python compare.py
# MT5-large-pytorch vs paddle MT5-large-paddle
mean difference: tensor(2.0390e-06)
max difference: tensor(0.0004)

(三)Weights Transform

run python convert.py,transform weights of huggingface model to weights of paddle model. The weight path needs to be replaced

(四)Downstream task fine-tuning

run python train.py. "args.py" is for parameter.

Reference

大佬的T5代码:https://github.com/JunnYu/paddle_t5

@unknown{unknown,
author = {Xue, Linting and Constant, Noah and Roberts, Adam and Kale, Mihir and Al-Rfou, Rami and Siddhant, Aditya and Barua, Aditya and Raffel, Colin},
year = {2020},
month = {10},
pages = {},
title = {mT5: A massively multilingual pre-trained text-to-text transformer}
}
Test finetuning of XLSR (multilingual wav2vec 2.0) for other speech classification tasks

wav2vec_finetune Test finetuning of XLSR (multilingual wav2vec 2.0) for other speech classification tasks Initial test: gender recognition on this dat

8 Aug 11, 2022
L3Cube-MahaCorpus a Marathi monolingual data set scraped from different internet sources.

L3Cube-MahaCorpus L3Cube-MahaCorpus a Marathi monolingual data set scraped from different internet sources. We expand the existing Marathi monolingual

21 Dec 17, 2022
Practical Machine Learning with Python

Master the essential skills needed to recognize and solve complex real-world problems with Machine Learning and Deep Learning by leveraging the highly popular Python Machine Learning Eco-system.

Dipanjan (DJ) Sarkar 2k Jan 08, 2023
Facilitating the design, comparison and sharing of deep text matching models.

MatchZoo Facilitating the design, comparison and sharing of deep text matching models. MatchZoo 是一个通用的文本匹配工具包,它旨在方便大家快速的实现、比较、以及分享最新的深度文本匹配模型。 🔥 News

Neural Text Matching Community 3.7k Jan 02, 2023
Blackstone is a spaCy model and library for processing long-form, unstructured legal text

Blackstone Blackstone is a spaCy model and library for processing long-form, unstructured legal text. Blackstone is an experimental research project f

ICLR&D 579 Jan 08, 2023
Optimal Transport Tools (OTT), A toolbox for all things Wasserstein.

Optimal Transport Tools (OTT), A toolbox for all things Wasserstein. See full documentation for detailed info on the toolbox. The goal of OTT is to pr

OTT-JAX 255 Dec 26, 2022
A modular Karton Framework service that unpacks common packers like UPX and others using the Qiling Framework.

Unpacker Karton Service A modular Karton Framework service that unpacks common packers like UPX and others using the Qiling Framework. This project is

c3rb3ru5 45 Jan 05, 2023
jiant is an NLP toolkit

jiant is an NLP toolkit The multitask and transfer learning toolkit for natural language processing research Why should I use jiant? jiant supports mu

ML² AT CILVR 1.5k Jan 04, 2023
This repository contains the code, models and datasets discussed in our paper "Few-Shot Question Answering by Pretraining Span Selection"

Splinter This repository contains the code, models and datasets discussed in our paper "Few-Shot Question Answering by Pretraining Span Selection", to

Ori Ram 88 Dec 31, 2022
A repository to run gpt-j-6b on low vram machines (4.2 gb minimum vram for 2000 token context, 3.5 gb for 1000 token context). Model loading takes 12gb free ram.

Basic-UI-for-GPT-J-6B-with-low-vram A repository to run GPT-J-6B on low vram systems by using both ram, vram and pinned memory. There seem to be some

90 Dec 25, 2022
Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.

CTC Decoding Algorithms Update 2021: installable Python package Python implementation of some common Connectionist Temporal Classification (CTC) decod

Harald Scheidl 736 Jan 03, 2023
Multi-Scale Temporal Frequency Convolutional Network With Axial Attention for Speech Enhancement

MTFAA-Net Unofficial PyTorch implementation of Baidu's MTFAA-Net: "Multi-Scale Temporal Frequency Convolutional Network With Axial Attention for Speec

Shimin Zhang 87 Dec 19, 2022
Implementation of COCO-LM, Correcting and Contrasting Text Sequences for Language Model Pretraining, in Pytorch

COCO LM Pretraining (wip) Implementation of COCO-LM, Correcting and Contrasting Text Sequences for Language Model Pretraining, in Pytorch. They were a

Phil Wang 44 Jul 28, 2022
Random-Word-Generator - Generates meaningful words from dictionary with given no. of letters and words.

Random Word Generator Generates meaningful words from dictionary with given no. of letters and words. This might be useful for generating short links

Mohammed Rabil 1 Jan 01, 2022
Rank-One Model Editing for Locating and Editing Factual Knowledge in GPT

Rank-One Model Editing (ROME) This repository provides an implementation of Rank-One Model Editing (ROME) on auto-regressive transformers (GPU-only).

Kevin Meng 130 Dec 21, 2022
PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

VAENAR-TTS - PyTorch Implementation PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

Keon Lee 67 Nov 14, 2022
Code for Findings of ACL 2022 Paper "Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors"

SWRM Code for Findings of ACL 2022 Paper "Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors" Clone Clone th

14 Jan 03, 2023
CodeBERT: A Pre-Trained Model for Programming and Natural Languages.

CodeBERT This repo provides the code for reproducing the experiments in CodeBERT: A Pre-Trained Model for Programming and Natural Languages. CodeBERT

Microsoft 1k Jan 03, 2023
Galois is an auto code completer for code editors (or any text editor) based on OpenAI GPT-2.

Galois is an auto code completer for code editors (or any text editor) based on OpenAI GPT-2. It is trained (finetuned) on a curated list of approximately 45K Python (~470MB) files gathered from the

Galois Autocompleter 91 Sep 23, 2022
p-tuning for few-shot NLU task

p-tuning_NLU Overview 这个小项目是受乐于分享的苏剑林大佬这篇p-tuning 文章启发,也实现了个使用P-tuning进行NLU分类的任务, 思路是一样的,prompt实现方式有不同,这里是将[unused*]的embeddings参数抽取出用于初始化prompt_embed后

3 Dec 29, 2022