bhatta1 commited on
Commit
bb371d9
1 Parent(s): 3de7205

Update README.md

Browse files

Added link to document annotation cookbook

Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -46,6 +46,11 @@ with torch.no_grad():
46
  ## Cookbook on Model Usage as a Guardrail
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
  ## Performance Comparison with Other Models
50
  The model outperforms most popular models with significantly lower inference latency. If a better F1 score is required, please refer to IBM's 12-layer model [here](https://huggingface.co/ibm-granite/granite-guardian-hap-125m).
51
 
 
46
  ## Cookbook on Model Usage as a Guardrail
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 Bulk HAP Annotations of Documents
51
+ This recipe illustrates the use of the model for bulk HAP annotation of documents. 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. [Document Annotation Cookbook](https://github.com/IBM/data-prep-kit/tree/dev/transforms/universal/hap/python)
52
+
53
+
54
  ## Performance Comparison with Other Models
55
  The model outperforms most popular models with significantly lower inference latency. If a better F1 score is required, please refer to IBM's 12-layer model [here](https://huggingface.co/ibm-granite/granite-guardian-hap-125m).
56