Project Baarat enhances accessibility to India's linguistic diversity through technology. It's an open-source initiative using LLMs for Indic-NLP tasks. Features include tokenizers for Indian languages and fine-tuned LLMs for accurate text generation. It fosters community-driven innovation and offers high-quality datasets for training. NOTE: The Kannada experts model is under development and is not meant to be used as of now. A future release will enable the model to be used for inference.
Project description
The author of this package has not provided a project description
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
baraat-0.0.1.tar.gz
(1.2 kB
view details)
File details
Details for the file baraat-0.0.1.tar.gz.
File metadata
- Download URL: baraat-0.0.1.tar.gz
- Upload date:
- Size: 1.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.1.1 pkginfo/1.4.2 requests/2.22.0 setuptools/45.2.0 requests-toolbelt/0.8.0 tqdm/4.30.0 CPython/3.8.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | d672396da594575374e1d0dc84c4d28718aa5bf3067d0b76d64b889ee9bae12d |
|
| MD5 | 2399ca74209b83a8b6eba03f13382478 |
|
| BLAKE2b-256 | f1bb3e6a99fe9460c5e06c7216ab0727375cd59b040916f4665d710792f93b10 |
