pronics2004
commited on
Commit
•
8f9b0f8
1
Parent(s):
5ac44d1
Update README.md
Browse files
README.md
CHANGED
@@ -47,7 +47,7 @@ with torch.no_grad():
|
|
47 |
This recipe illustrates the use of the model either in a prompt, the output, or both. This is an example of a “guard rail” typically used in generative AI applications for safety.
|
48 |
[Guardrail Cookbook](https://github.com/ibm-granite-community/granite-code-cookbook/blob/main/recipes/Guard-Rails/HAP.ipynb)
|
49 |
|
50 |
-
## Cookbook on Model Usage for HAP Annotation on Documents in Bulk using [Data Prep Kit]
|
51 |
This recipe illustrates the use of the model for HAP annotation of documents in bulk. The documents are read from a parquet file. It is then fed to the model sentence by sentence for a document and a HAP score for the document is decided. This is then stored back in the parquet file. Here is the sample cookbook for it [Data Prep Kit Cookbook](https://github.com/IBM/data-prep-kit/tree/dev/transforms/universal/hap/python)
|
52 |
|
53 |
|
|
|
47 |
This recipe illustrates the use of the model either in a prompt, the output, or both. This is an example of a “guard rail” typically used in generative AI applications for safety.
|
48 |
[Guardrail Cookbook](https://github.com/ibm-granite-community/granite-code-cookbook/blob/main/recipes/Guard-Rails/HAP.ipynb)
|
49 |
|
50 |
+
## Cookbook on Model Usage for HAP Annotation on Documents in Bulk using [Data Prep Kit](https://github.com/IBM/data-prep-kit)
|
51 |
This recipe illustrates the use of the model for HAP annotation of documents in bulk. The documents are read from a parquet file. It is then fed to the model sentence by sentence for a document and a HAP score for the document is decided. This is then stored back in the parquet file. Here is the sample cookbook for it [Data Prep Kit Cookbook](https://github.com/IBM/data-prep-kit/tree/dev/transforms/universal/hap/python)
|
52 |
|
53 |
|