Easily deploy HuggingFace Transformers on a website
Project description
🚀 Deploy Transformers 🤗
Deploy a SOTA model for text-generation in just three lines of code 💻
Installation
Pytorch and Transformers are obviously needed.
pip install deploy-transformers
For deployment, file structure needs to be like this:
├── static
│ ├── script.js
│ ├── style.css
├── templates
│ ├── 404.html
│ ├── index.html
|
└── your_file.py
You can either clone this repository to have original files or use the function website.create_structure()
or create yourself the structure.
website.create_structure()
will automatically create templates/, static/ and all the files that are in it (.html, .js, .css).
Usage
Check the examples/ folder.
# Deployment
from deploy_transformers import Website
website = Website(model_type="gpt2", model_name="distilgpt2")
# website.create_folder(homepage_file="index.html", template_folder='templates', static_folder='static')
website.deploy()
You can change homepage filename, templates/ and static/ names in website.deploy()
but it's better to keep them as default.
# Only text generation
from deploy_transformers import ListModels, Model
# ListModels() to show available models
model = Model("gpt2", "distilgpt2", seed=42, verbose=False)
model.generate(length=20, prompt="The quick brown fox jumps over the lazy dog")
# If no prompt, input will be ask until exit
## Thanks
- Transformers package by HuggingFace
- gpt-2-cloudrun by minimaxir
Notes
- Do the same but for other tasks like sentiment analysis, or Q&A.
- Add Flask option?
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
Built Distribution
File details
Details for the file deploy-transformers-0.1.tar.gz
.
File metadata
- Download URL: deploy-transformers-0.1.tar.gz
- Upload date:
- Size: 12.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/42.0.2 requests-toolbelt/0.9.1 tqdm/4.40.2 CPython/3.7.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 |
eced19978a4f4f3d6231dd6b016416f67cdba9404e0e8165f57c27433798b5f7
|
|
MD5 |
c57d60d67bb2c60acc773cc56b913536
|
|
BLAKE2b-256 |
4588d12c553f0910660974764d2d2ecdaf5ad28d50ced472bdce1611d0796294
|
File details
Details for the file deploy_transformers-0.1-py3-none-any.whl
.
File metadata
- Download URL: deploy_transformers-0.1-py3-none-any.whl
- Upload date:
- Size: 15.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/42.0.2 requests-toolbelt/0.9.1 tqdm/4.40.2 CPython/3.7.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 |
c5d0fe946be7cebeb46d622b6717af4ae171e326b0feb24d6c4570ab7005cf01
|
|
MD5 |
21fb02f0dc030082aac6485dad40bdd1
|
|
BLAKE2b-256 |
d8277f06939c3c4663dd88a043565b50e896fbf2f622932a2199d5c99243d454
|