Update README.md

README.md

@@ -1,5 +1,46 @@
----
-license: other
-license_name: govtech-singapore
-license_link: LICENSE
----
+---
+license: other
+license_name: govtech-singapore
+license_link: LICENSE
+language:
+- en
+- ms
+- ta
+- zh
+pipeline_tag: text-classification
+tags:
+- classifier
+- safety
+- moderation
+- multilingual
+---
+
+# LionGuard 2
+LionGuard 2 is a multilingual content moderation classifier tuned for English/Singlish, Chinese, Malay, and Tamil in the Singapore context. 
+
+It leverages OpenAI’s `text-embedding-3-large` with a multi-head classifier to return fine-grained scores for the following categories:
+- Overall safety (`binary`)
+- Hate (`hateful_l1`, `hateful_l2`)
+- Insults (`insults`)
+- Sexual content (`sexual_l1`, `sexual_l2`)
+- Physical violence (`physical_violence`)
+- Self-harm (`self_harm_l1`, `self_harm_l2`)
+- Other misconduct (`all_other_misconduct_l1`, `all_other_misconduct_l2`)
+
+---
+
+# Usage
+1. Install packages
+```bash
+pip install -r requirements.txt
+```
+
+2. Set your OpenAI key
+```bash
+export OPENAI_API_KEY=sk-...
+```
+
+3. Run inference on an array of texts
+```bash
+python inference.py "['Text 1', 'Text 2']"
+```