Package for training ande deploying doctrinally correct LLMs.
Project description
aiforthechurch
Modern LLMs are rooted in secular value systems that are often misaligned with religious organisations. This PyPI package allows anyone to train and deploying doctrinally correct LLMs based on Llama2. Effectively, we are aligning models to a set of values.
from aiforthecurch import align_llama2
doctrinal_dataset = "/path/to/csv"
align_llama2(doctrinal_dataset)
aiforthechurch
is integrated with HuggingFace shuch that the aligned model will be automatically pushed to your HuggingFace repo of choice at the end of the training.
At aiforthechurch.org we provide tools for generating doctrinal datasets, a few examples are available at huggingface.co/AiForTheChurch.
Project details
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 aiforthechurch-0.2.tar.gz
.
File metadata
- Download URL: aiforthechurch-0.2.tar.gz
- Upload date:
- Size: 1.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3a340b71eecb161d1e1e569747af48d7937e5a6aa22a73399890c9b8da2f5a95 |
|
MD5 | c81886dc8d313408b72dce0e43171719 |
|
BLAKE2b-256 | 93fe8ee40acbc5ee7c3784d8bac458d45a997ad43b6a381290dceb90d92836bd |
Provenance
File details
Details for the file aiforthechurch-0.2-py3-none-any.whl
.
File metadata
- Download URL: aiforthechurch-0.2-py3-none-any.whl
- Upload date:
- Size: 1.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6a85a48e71740337f45e98e7706f91da9652bcc6049cd875f8766133eef3830a |
|
MD5 | da344b826cc967df662a2098dcf13884 |
|
BLAKE2b-256 | 4804f752d20d1ead54fa92c18b19c5f026b3093a9031832d8002a198c30520d1 |