Upload folder using huggingface_hub
Browse files- hate_speech_demo.py +3 -3
hate_speech_demo.py
CHANGED
|
@@ -778,19 +778,19 @@ def create_gradio_app():
|
|
| 778 |
|
| 779 |
gr.HTML(policy_popup_html)
|
| 780 |
|
| 781 |
-
gr.Markdown("#
|
| 782 |
gr.HTML("""
|
| 783 |
<div style="margin-bottom: 20px;">
|
| 784 |
<p>
|
| 785 |
<strong>Assess whether user-generated social content contains hate speech using Contextual AI's State-of-the-Art Agentic RAG system.</strong>
|
| 786 |
</p>
|
| 787 |
<p>
|
| 788 |
-
Contextual's Safety Oracle classifications are steerable and explainable as they are based on a policy document rather than parametric knowledge. This app returns ratings from LlamaGuard 3.0, the OpenAI Moderation API and the Perspective API from Google Jigsaw for comparison. This is a demo from Contextual AI researchers. Feedback is welcome as we work with design partners to bring this to production. Reach out to Aravind Mohan, Head of Data Science, at [email protected].
|
| 789 |
</p>
|
| 790 |
|
| 791 |
<h2>Instructions</h2>
|
| 792 |
<ul>
|
| 793 |
-
<p>Enter user-generated content to receive an assessment from all four models, or use the 'Random Test Case' button to generate an example
|
| 794 |
<p><strong>Safety warning.</strong>Some of the randomly generated test cases contain hateful language that you might find offensive or upsetting.</p>
|
| 795 |
</ul>
|
| 796 |
|
|
|
|
| 778 |
|
| 779 |
gr.HTML(policy_popup_html)
|
| 780 |
|
| 781 |
+
gr.Markdown("# Safety Oracle for Rating Hate Speech [BETA]")
|
| 782 |
gr.HTML("""
|
| 783 |
<div style="margin-bottom: 20px;">
|
| 784 |
<p>
|
| 785 |
<strong>Assess whether user-generated social content contains hate speech using Contextual AI's State-of-the-Art Agentic RAG system.</strong>
|
| 786 |
</p>
|
| 787 |
<p>
|
| 788 |
+
Contextual's Safety Oracle classifications are steerable and explainable as they are based on a policy document rather than parametric knowledge. This app returns ratings from LlamaGuard 3.0, the OpenAI Moderation API and the Perspective API from Google Jigsaw for comparison. This is a demo from Contextual AI researchers. Feedback is welcome as we work with design partners to bring this to production. Reach out to Aravind Mohan, Head of Data Science, at <a href="mailto:[email protected]">aravind.[email protected]</a>.
|
| 789 |
</p>
|
| 790 |
|
| 791 |
<h2>Instructions</h2>
|
| 792 |
<ul>
|
| 793 |
+
<p>Enter user-generated content to receive an assessment from all four models, or use the 'Random Test Case' button to generate an example. \n</p>
|
| 794 |
<p><strong>Safety warning.</strong>Some of the randomly generated test cases contain hateful language that you might find offensive or upsetting.</p>
|
| 795 |
</ul>
|
| 796 |
|