自然语言处理(NLP)
Project description
📌 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
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nlhappy-2024.5.7.post1.tar.gz
(90.5 kB
view details)
Built Distribution
File details
Details for the file nlhappy-2024.5.7.post1.tar.gz
.
File metadata
- Download URL: nlhappy-2024.5.7.post1.tar.gz
- Upload date:
- Size: 90.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.7.1 CPython/3.10.10 Linux/4.4.0-62-generic
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8669465ddb3cf6b660afc507d51680b85bdc6ed2ce40165fde70bcf703ccdc10 |
|
MD5 | e2a277ac7c2cef466c588f0ae4eacbb1 |
|
BLAKE2b-256 | 48bbd9ec0ea3e325f6fd8150d0a44ef3a3c6261213a41e6b116d913d61a953ba |
File details
Details for the file nlhappy-2024.5.7.post1-py3-none-any.whl
.
File metadata
- Download URL: nlhappy-2024.5.7.post1-py3-none-any.whl
- Upload date:
- Size: 155.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.7.1 CPython/3.10.10 Linux/4.4.0-62-generic
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | adedb7267eb933dc52325b9e0b8dbf4cc94edcd4c8651ed84cc469d513eabeff |
|
MD5 | a5ed8d4f7a18974f2d7d9b2f326df02e |
|
BLAKE2b-256 | 9caa88f675b17157afe9887c8a8de0b2026bab1916032aa1de6a259072ec908f |