Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -23,3 +23,10 @@ align_llama2(doctrinal_dataset)
|
|
23 |
`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.
|
24 |
|
25 |
At [aiforthechurch.org](aiforthechurch.org) we provide tools for generating doctrinal datasets, a few of which are made available here, and further instructions.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
`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.
|
24 |
|
25 |
At [aiforthechurch.org](aiforthechurch.org) we provide tools for generating doctrinal datasets, a few of which are made available here, and further instructions.
|
26 |
+
|
27 |
+
#Model details
|
28 |
+
|
29 |
+
|
30 |
+
Training requirements:
|
31 |
+
- GPU with over 16GB of memory (we trained on NVIDIA Tesla V100 32GB and NVIDIA Ampere A6000 45GB)
|
32 |
+
- 30GB of RAM (the raw model weights are about 29GB, our models are cast to 8bit to use less memory)
|