超轻量级bert的pytorch版本,大量中文注释,容易修改结构,持续更新

Overview

bert4pytorch

2021年8月27更新:

感谢大家的star,最近有小伙伴反映了一些小的bug,我也注意到了,奈何这个月工作上实在太忙,更新不及时,大约会在9月中旬集中更新一个只需要pip一下就完全可用的版本,然后会新添加一些关键注释。 再增加对抗训练的内容,更新一个完整的finetune案例。

背景

目前最流行的pytorch版本的bert框架,莫过于huggingface团队的Transformers项目,但是随着项目的越来越大,显得很重,对于初学者、有一定nlp基础的人来说,想看懂里面的代码逻辑,深入了解bert,有很大的难度。

另外,如果想修改Transformers的底层代码也是想当困难的,导致很难对模型进行魔改。

本项目把整个bert架构,浓缩在几个文件当中(主要修改自Transfomers开源项目),删除大量无关紧要的代码,新增了一些功能,比如:ema、warmup schedule,并且在核心部分,添加了大量中文注释,力求解答读者在使用过程中产生的一些疑惑。

此项目核心只有三个文件,modeling、tokenization、optimization。并且都在几百行内完成。结合大量的中文注释,分分钟透彻理解bert。

功能

现在已经实现

  • 加载bert、RoBERTa-wwm-ext的预训练权重进行fintune
  • 实现了带warmup的优化器
  • 实现了模型权重的指数滑动平均(ema)

未来将实现

  • albert、GPT、XLnet等网络架构
  • 实现对抗训练、conditional Layer Norm等功能(想法来自于苏神(苏剑林)的bert4keras开源项目,事实上,bert4pytorch就是受到了它的启发)
  • 添加大量的例子和中文注释,减轻学习难度

安装

pip install bert4pytorch==0.1.2

使用

  • 加载预训练模型
from bert4pytorch.modeling import BertModel, BertConfig
from bert4pytorch.tokenization import BertTokenizer
from bert4pytorch.optimization import AdamW, get_linear_schedule_with_warmup
import torch

model_path = "/model/pytorch_bert_pretrain_model"
config = BertConfig(model_path + "/config.json")

tokenizer = BertTokenizer(model_path + "/vocab.txt")
model = BertModel.from_pretrained(model_path, config)

input_ids, token_type_ids = tokenizer.encode("今天很开心")

input_ids = torch.tensor([input_ids])
token_type_ids = torch.tensor([token_type_ids])

model.eval()

outputs = model(input_ids, token_type_ids, output_all_encoded_layers=True)

## orther code
  • 带warmup的优化器实现
param_optimizer = list(model.named_parameters())
no_decay = ['bias', 'LayerNorm.bias', 'LayerNorm.weight']
optimizer_grouped_parameters = [
    {'params': [p for n, p in param_optimizer
                if not any(nd in n for nd in no_decay)], 'weight_decay': 0.01},
    {'params': [p for n, p in param_optimizer
                if any(nd in n for nd in no_decay)], 'weight_decay': 0.0}
]
optimizer = AdamW(optimizer_grouped_parameters, lr=1e-5, correct_bias=False)

num_training_steps=train_batches * num_epoches
num_warmup_steps=num_training_steps * warmup_proportion
schedule = get_linear_schedule_with_warmup(optimizer, num_warmup_steps, num_training_steps)

其他

最初整理这个项目,只是为了自己方便。这一段时间,经常逛苏剑林大佬的博客,里面的内容写得相当精辟,更加感叹的是, 苏神经常能闭门造车出一些还不错的trick,只能说,大佬牛逼。

所以本项目命名也雷同bert4keras,以感谢苏大佬无私的分享。

后来,慢慢萌生把学习中的小小成果开源出来,后期会渐渐补充例子,前期会借用苏神的bert4keras里面的例子,实现pytorch版本。如果有问题,欢迎讨论;如果本项目对您有用,请不吝star!

Owner
muqiu
muqiu
Code for paper: An Effective, Robust and Fairness-awareHate Speech Detection Framework

BiQQLSTM_HS Code and data for paper: Title: An Effective, Robust and Fairness-awareHate Speech Detection Framework. Authors: Guanyi Mou and Kyumin Lee

Guanyi Mou 2 Dec 27, 2022
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Provides an implementation of today's most used tokenizers, with a focus on performance and versatility. Main features: Train new vocabularies and tok

Hugging Face 6.2k Dec 31, 2022
The code from the whylogs workshop in DataTalks.Club on 29 March 2022

whylogs Workshop The code from the whylogs workshop in DataTalks.Club on 29 March 2022 whylogs - The open source standard for data logging (Don't forg

DataTalksClub 12 Sep 05, 2022
A Japanese tokenizer based on recurrent neural networks

Nagisa is a python module for Japanese word segmentation/POS-tagging. It is designed to be a simple and easy-to-use tool. This tool has the following

325 Jan 05, 2023
File-based TF-IDF: Calculates keywords in a document, using a word corpus.

File-based TF-IDF Calculates keywords in a document, using a word corpus. Why? Because I found myself with hundreds of plain text files, with no way t

Jakob Lindskog 1 Feb 11, 2022
Transformer training code for sequential tasks

Sequential Transformer This is a code for training Transformers on sequential tasks such as language modeling. Unlike the original Transformer archite

Meta Research 578 Dec 13, 2022
Unofficial Implementation of Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration

Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration This repo contains only model Implementation of Zero-Shot Text-to-Speech for Text

Rishikesh (ऋषिकेश) 33 Sep 22, 2022
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

T5: Text-To-Text Transfer Transformer The t5 library serves primarily as code for reproducing the experiments in Exploring the Limits of Transfer Lear

Google Research 4.6k Jan 01, 2023
Correctly generate plurals, ordinals, indefinite articles; convert numbers to words

NAME inflect.py - Correctly generate plurals, singular nouns, ordinals, indefinite articles; convert numbers to words. SYNOPSIS import inflect p = in

Jason R. Coombs 762 Dec 29, 2022
Implementation of ProteinBERT in Pytorch

ProteinBERT - Pytorch (wip) Implementation of ProteinBERT in Pytorch. Original Repository Install $ pip install protein-bert-pytorch Usage import torc

Phil Wang 92 Dec 25, 2022
Sentiment-Analysis and EDA on the IMDB Movie Review Dataset

Sentiment-Analysis and EDA on the IMDB Movie Review Dataset The main part of the work focuses on the exploration and study of different approaches whi

Nikolas Petrou 1 Jan 12, 2022
Ongoing research training transformer language models at scale, including: BERT & GPT-2

Megatron (1 and 2) is a large, powerful transformer developed by the Applied Deep Learning Research team at NVIDIA.

NVIDIA Corporation 3.5k Dec 30, 2022
Extract city and country mentions from Text like GeoText without regex, but FlashText, a Aho-Corasick implementation.

flashgeotext ⚡ 🌍 Extract and count countries and cities (+their synonyms) from text, like GeoText on steroids using FlashText, a Aho-Corasick impleme

Ben 57 Dec 16, 2022
Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

Alexander Veysov 3.2k Dec 31, 2022
Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation This is the official PyTorch implementation

Salesforce 564 Jan 08, 2023
Yes it's true :broken_heart:

Information WARNING: No longer hosted If you would like to be on this repo's readme simply fork or star it! Forks 1 - Flowzii 2 - Errorcrafter 3 - vk-

Dropout 66 Dec 31, 2022
Package for controllable summarization

summarizers summarizers is package for controllable summarization based CTRLsum. currently, we only supports English. It doesn't work in other languag

Hyunwoong Ko 72 Dec 07, 2022
TweebankNLP - Pre-trained Tweet NLP Pipeline (NER, tokenization, lemmatization, POS tagging, dependency parsing) + Models + Tweebank-NER

TweebankNLP This repo contains the new Tweebank-NER dataset and off-the-shelf Twitter-Stanza pipeline for state-of-the-art Tweet NLP, as described in

Laboratory for Social Machines 84 Dec 20, 2022
A simple version of DeTR

DeTR-Lite A simple version of DeTR Before you enjoy this DeTR-Lite The purpose of this project is to allow you to learn the basic knowledge of DeTR. P

Jianhua Yang 11 Jun 13, 2022
A fast and easy implementation of Transformer with PyTorch.

FasySeq FasySeq is a shorthand as a Fast and easy sequential modeling toolkit. It aims to provide a seq2seq model to researchers and developers, which

宁羽 7 Jul 18, 2022