Metadata-Version: 2.1
Name: deepse
Version: 0.0.1
Summary: **DeepSE**: **Sentence Embeddings** based on Deep Nerual Networks, designed for **PRODUCTION** enviroment!
Home-page: https://github.com/luozhouyang/deepse
Author: ZhouYang Luo
Author-email: zhouyang.luo@gmail.com
License: Apache Software License
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Description-Content-Type: text/markdown
Requires-Dist: transformers-keras (>=0.2.6)
Requires-Dist: tokenizers
Provides-Extra: tf
Requires-Dist: tensorflow (>=2.0.1) ; extra == 'tf'
Provides-Extra: tf-gpu
Requires-Dist: tensorflow-gpu (>=2.0.1) ; extra == 'tf-gpu'

# DeepSE
**DeepSE**: **Sentence Embeddings** based on Deep Nerual Networks, designed for **PRODUCTION** enviroment!

## Installation

Clone git repo:

```bash
git clone https://github.com/luozhouyang/deepse.git
```

or install from pypi:

```bash
pip install -U deepse
```

## SimCSE

Train a **Unsup SimCSE** model in one line:
```bash
PRETRAINED_MODEL_PATH=/path/to/your/pretrained/bert/dir python run_simcse.py
```

> You can modify the parameters in `run_simcse.py` as you need.




