Update README.md (#1)
Browse files- Update README.md (84c428863a567f76413dac7edcf8671501ab6aae)
Co-authored-by: Bishwaranjan Bhattacharjee <bhatta1@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -42,6 +42,10 @@ with torch.no_grad():
|
|
| 42 |
probability = torch.softmax(logits, dim=1).detach().numpy()[:,1].tolist() # Probability of toxicity.
|
| 43 |
|
| 44 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
## Performance Comparison with Other Models
|
| 46 |
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).
|
| 47 |
|
|
|
|
| 42 |
probability = torch.softmax(logits, dim=1).detach().numpy()[:,1].tolist() # Probability of toxicity.
|
| 43 |
|
| 44 |
```
|
| 45 |
+
|
| 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 |
|