pybert

安装

>pip install pybert

预训练模型

下载地址：

bert_Chinese 模型文件: https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese.tar.gz
词表 https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese-vocab.txt
【备用】百度网盘：https://pan.baidu.com/s/1HPZBvkMAyu0nDUqHWsb0SA?pwd=abbn

所需文件：

pytorch_model.bin
bert_config.json
vocab.txt

放到 bert_pretrain 文件夹中

训练数据下载

THUCNews

可以任意指定文件夹名称，训练数据的格式要和上面一致

训练和预测

训练

from pybert.models import bert
from pybert.train_eval import load_and_train

dataset = 'THUCNews'  # 数据集
logfile = 'log.txt'  # 日志文件
config = bert.Config(dataset, logfile=logfile)
load_and_train(config)

预测

# coding: UTF-8
import pybert.models.bert as bert
from pybert.train_eval import Prediction

config = bert.Config(dataset='THUCNews')
prediction = Prediction(config)

sentences = ['野兽用纪录打爆第二中锋 掘金版三巨头已巍然成型', '56所高校预估2009年湖北录取分数线出炉']

predict_label, score = prediction.predict(sentences)
print("predict label:")
print(predict_label)

对应论文

[1] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Metadata

Release files for pybert 0.0.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pybert 0.0.2
File	Size	Uploaded	Provenance
pybert-0.0.2.tar.gz	28.6 kB	Dec 29, 2022	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for pybert 0.0.2
File	Interpreter	ABI	Platform	Reset
pybert-0.0.2-py3-none-any.whl 29.9 kB Dec 29, 2022 Without provenance	Python 3	none	any	Details

Total release size: 58.5 kB

Release files / pybert-0.0.2.tar.gz

Download URL	pybert-0.0.2.tar.gz
Size	28.6 kB
Tags	Source
SHA-256 checksum How to use checksums	`88a558d14930ed546ff827e189955c8448dfdb90a06d3350e260fa34a32a1f93`
BLAKE2b-256 checksum How to use checksums	`49f1372bd98b5ae7ebce3906ee284cb5fd507dcf9e897f020be7f1733f73e1e3`
Upload date	Dec 29, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.1 importlib_metadata/3.10.0 pkginfo/1.6.1 requests/2.24.0 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.8.5`

Release files / pybert-0.0.2-py3-none-any.whl

Download URL	pybert-0.0.2-py3-none-any.whl
Size	29.9 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`c8ffa6ccfd44232ada27082d285690c8cbda9b363c4c20f284365796151116d4`
BLAKE2b-256 checksum How to use checksums	`baee4873531be4c3c307749b15bd894ae38c805a16902c5acbaf0787a6bf1ddf`
Upload date	Dec 29, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.1 importlib_metadata/3.10.0 pkginfo/1.6.1 requests/2.24.0 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.8.5`

Security for pybert 0.0.2

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.0.2 This release

Dec 29, 2022 2 release files No provenance

0.0.1

Dec 24, 2022 2 release files No provenance

pybert 0.0.2