Make Pad Thai From few-shot learning 😉
Project description
Pad Thai
Make Pad Thai from few-shot learning 😉.
PadThai is a language model tool with an application for few-shot learning for Thai Language.
- Original code from: https://link.medium.com/4FfbALWz8gb
- Documentation: https://pythainlp.github.io/padthai/
- Tutorials: https://github.com/PyThaiNLP/padthai/tree/main/notebooks
Install
pip install padthai
Support Model
- GPT-Neo - GPT-Neo is a transformer model designed using EleutherAI's replication of the GPT-3 architecture.
- ThaiGPT-Next - It is fine-tune the GPT-Neo model for Thai language.
- Flax GPT-2 model - It's GPT-2 model. It was trained on the OSCAR dataset
Requirements
transformers<5.0
License
Apache-2.0 License
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
padthai-0.1.1.tar.gz
(4.4 kB
view details)
Built Distribution
padthai-0.1.1-py3-none-any.whl
(11.2 kB
view details)
File details
Details for the file padthai-0.1.1.tar.gz
.
File metadata
- Download URL: padthai-0.1.1.tar.gz
- Upload date:
- Size: 4.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.6.3 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.0 CPython/3.9.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6901ce3a122f52dc34741f53b3ae72877a6a2e8001f3f7cd3d9167ce49678680 |
|
MD5 | e78458d7b7ee0e5cfe0098ec1c706b4c |
|
BLAKE2b-256 | 55be9cb1c34c0bfa649712b467974d4f8326aa75b9c883fc23a57f11d91c8d6c |
File details
Details for the file padthai-0.1.1-py3-none-any.whl
.
File metadata
- Download URL: padthai-0.1.1-py3-none-any.whl
- Upload date:
- Size: 11.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.6.3 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.0 CPython/3.9.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b9bfe7c59e58b97edc1639ef6f3451f124d517f9a6219a0893c11cbdb61b25bf |
|
MD5 | 684875e2e97f2f0a607f910d5f640285 |
|
BLAKE2b-256 | 84db552cc86249a234a47d414910a708d805ec93e12a14d43dbc16c0ee7e4e97 |