📌 简介
nlhappy致力于复现自然语言处理各类任务的SOTA模型(不包含LLM相关任务)。
文档地址:
它主要的依赖有
- transformers: 下载预训练权重
- pytorch-lightning: 模型训练
- datasets: 构建数据集
- pydantic: 数据校验
📌 支持NLP任务
- 实体抽取
- 嵌套实体抽取
- 非连续实体抽取
- 关系抽取
- 事件抽取
- 文本单标签分类
- 文本多标签分类
- 阅读理解
- 文本对分类
- 文本对相似度(文本向量化)
📌 安装
安装nlhappy
推荐先去pytorch官网安装pytorch和对应cuda
# pip 安装
pip install --upgrade pip
pip install --upgrade nlhappy
其他可选
推荐安装wandb用于可视化训练日志
- 安装:
pip install wandb
- 注册: https://wandb.ai/
- 获取认证: https://wandb.ai/authorize
- 登陆:
wandb login
- 使用
# 命令行训练
nlhappy datamodule=xxx model=xxx trainer=xxx logger=wandb
模型训练开始后去官网查看训练实况
1 maintainer
Metadata
1 maintainer
Release files for nlhappy 2024.5.7.post1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| nlhappy-2024.5.7.post1.tar.gz | 90.5 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| nlhappy-2024.5.7.post1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 246.2 kB
Release files / nlhappy-2024.5.7.post1.tar.gz
| Download URL | nlhappy-2024.5.7.post1.tar.gz |
|---|---|
| Size | 90.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8669465ddb3cf6b660afc507d51680b85bdc6ed2ce40165fde70bcf703ccdc10
|
|
BLAKE2b-256 checksum How to use checksums |
48bbd9ec0ea3e325f6fd8150d0a44ef3a3c6261213a41e6b116d913d61a953ba
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.7.1 CPython/3.10.10 Linux/4.4.0-62-generic
|
Release files / nlhappy-2024.5.7.post1-py3-none-any.whl
| Download URL | nlhappy-2024.5.7.post1-py3-none-any.whl |
|---|---|
| Size | 155.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
adedb7267eb933dc52325b9e0b8dbf4cc94edcd4c8651ed84cc469d513eabeff
|
|
BLAKE2b-256 checksum How to use checksums |
9caa88f675b17157afe9887c8a8de0b2026bab1916032aa1de6a259072ec908f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.7.1 CPython/3.10.10 Linux/4.4.0-62-generic
|
