unified embedding model
Project description
uniem
unified embedding model
Install
pip install uniem
Usage
from uniem import UniEmbedder
embedder = UniEmbedder.from_pretrained('uniem/base-softmax-last-mean')
embeddings = embedder.encode(['Hello World!', '你好,世界!'])
Train Your Model
- create virtual environment
conda create -n uniem python=3.10
- install uniem
pip install -e .
- get help
python scripts/train_medi.py --help
- train embedding model
python scripts/train_medi.py <model_path_or_name> <data_file>
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
uniem-0.1.1.tar.gz
(12.7 kB
view details)
Built Distribution
uniem-0.1.1-py3-none-any.whl
(14.0 kB
view details)
File details
Details for the file uniem-0.1.1.tar.gz.
File metadata
- Download URL: uniem-0.1.1.tar.gz
- Upload date:
- Size: 12.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.2.0b3 CPython/3.9.12 Darwin/22.2.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 4a358d1bf0334aa447b5c7749ae0e1b38fce46f41d4061fbb5a7febc1e9b170a |
|
| MD5 | 0d831760c703eca4f4da82ace3500616 |
|
| BLAKE2b-256 | f4567ff1355f5ca027829834663741cbe42d533b1784154fa6d4b17cd9c9f47c |
Provenance
File details
Details for the file uniem-0.1.1-py3-none-any.whl.
File metadata
- Download URL: uniem-0.1.1-py3-none-any.whl
- Upload date:
- Size: 14.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.2.0b3 CPython/3.9.12 Darwin/22.2.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 912b89543b2fd5ae2ec44bba078a06595d0ab3411e9bf568f579c7eaef532304 |
|
| MD5 | 5e8e796ec1f478461da9f1ab5647a9b5 |
|
| BLAKE2b-256 | d0df30b35d54ac957f73551d6445bd4263d1d005f83a49346d13f1d6d8cc0865 |
