Update README.md
Browse files
README.md
CHANGED
@@ -190,10 +190,12 @@ Ethical use: Technology can have a profound impact on people and the world, and
|
|
190 |
|
191 |
## Limitations
|
192 |
|
193 |
-
The model was trained on the data that contains toxic language and societal biases originally crawled from the Internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts.
|
194 |
|
195 |
The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.
|
196 |
|
|
|
|
|
197 |
## Contact
|
198 |
|
199 |
E-Mail: [Zhilin Wang](mailto:[email protected])
|
|
|
190 |
|
191 |
## Limitations
|
192 |
|
193 |
+
The model was trained on the data that contains toxic language and societal biases originally crawled from the Internet. Therefore, the model may amplify those biases and return toxic responses especially when prompted with toxic prompts.
|
194 |
|
195 |
The model may generate answers that may be inaccurate, omit key information, or include irrelevant or redundant text producing socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive.
|
196 |
|
197 |
+
We recommend deploying the model with [NeMo Guardrails](https://github.com/NVIDIA/NeMo-Guardrails) to mitigate these potential issues.
|
198 |
+
|
199 |
## Contact
|
200 |
|
201 |
E-Mail: [Zhilin Wang](mailto:[email protected])
|