Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -7,4 +7,18 @@ sdk: static
|
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
-
Modern LLMs are rooted in secular value systems that are often misaligned with
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
pinned: false
|
8 |
---
|
9 |
|
10 |
+
Modern LLMs are rooted in secular value systems that are often misaligned with christian organisations. AI for the Church allows anyone to train and deploying doctrinally correct LLMs based on Llama2. Effectively, we are aligning models to a set of values.
|
11 |
+
This HF page is for storing models rooted in christian doctrine.
|
12 |
+
|
13 |
+
`pip install aiforthechurch` to install the PyPI package.
|
14 |
+
|
15 |
+
|
16 |
+
```python
|
17 |
+
from aiforthechurch import align_llama2
|
18 |
+
doctrinal_dataset = "/path/to/csv"
|
19 |
+
align_llama2(doctrinal_dataset)
|
20 |
+
```
|
21 |
+
|
22 |
+
`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.
|
23 |
+
|
24 |
+
At aiforthechurch.org we provide tools for generating doctrinal datasets, a few example datasets are made available here.
|