Transformer-based models implemented in tensorflow 2.x(Keras)
Project description
transformers-keras
基于tf.keras
的Transformers系列模型实现。
所有的Model
都是keras模型,可以直接用于训练模型、评估模型或者导出模型用于部署。
在线文档:transformers-keras文档
本库功能预览:
- 加载各种预训练模型的权重
- 掩码语言模型(Masked Language Model)解决方案
- 句向量(Sentence Embedding)的解决方案
- 抽取式问答任务(Question Answering)的解决方案
- 序列分类任务(Sequence Classification)的解决方案
- 序列标注任务(Token Classification)的解决方案
- 知识蒸馏(Knowledge Distillation)的框架
以上任务的数据处理、模型构建都完成了,可以一键开始训练。这里有两个例子:
更多使用方法和介绍,请查看在线文档:transformers-keras文档
联系方式
由于二维码过期限制,加微信讨论群请先加我微信邀请加入。
- 微信: luozhouyang0528
- 邮箱: zhouyang.luo@gmail.com
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
transformers_keras-0.5.1.tar.gz
(39.1 kB
view details)
Built Distribution
File details
Details for the file transformers_keras-0.5.1.tar.gz
.
File metadata
- Download URL: transformers_keras-0.5.1.tar.gz
- Upload date:
- Size: 39.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.6.0 importlib_metadata/4.8.2 pkginfo/1.8.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.10.0
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 17b82ef9e1f8ab68aa06a6f3ad47b0fe098a49d5099d5b4c161e3b26c8155070 |
|
MD5 | f5c98d1aea9a8563b65b3b0620831767 |
|
BLAKE2b-256 | 0a67272ae2a1a97ef08b8a20b341a6d12ea81892208fc80665da59e3d177bcc6 |
File details
Details for the file transformers_keras-0.5.1-py3-none-any.whl
.
File metadata
- Download URL: transformers_keras-0.5.1-py3-none-any.whl
- Upload date:
- Size: 63.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.6.0 importlib_metadata/4.8.2 pkginfo/1.8.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.10.0
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d2fec3e03db42c7b0c5eb4a14453d564ad5a0d3d1262605ec2812f7762201724 |
|
MD5 | bf00d5b4c2ddd84fe54965549b3b9664 |
|
BLAKE2b-256 | c65ad2e29df27ca3b23cbcde8a81a904c1b1e61008ffb8a35d2510c2f9f51262 |