Update README.md

README.md

@@ -43,4 +43,28 @@ The model was fine-tuned on a custom KoaliPi dataset covering:
 ## Instruction Format
 No system prompt needed. Uses ChatML format:
 
-**Document parsing:**
+**Document parsing:**
+
+Parse this document. Return ONLY a valid JSON with these fields:
+
+topics, difficulty, subject, key_concepts, has_equations, equations, summary.
+
+No explanation, just JSON.
+
+**MCQ generation:**
+Generate 3 multiple choice questions about {topic}.
+
+Return ONLY valid JSON array.
+
+**Filipino Q&A:**
+{question in Filipino or English}
+
+## Intended Use
+- Filipino high school and college STEM students
+- On-device inference via llama.rn
+- Part of the KoaliPi AI study app
+
+## Limitations
+- mmproj (vision encoder) not yet exportable via llama.cpp for Qwen2.5-VL
+- Image/VL features require mmproj — text features fully functional
+- 30 training steps — suitable for demo, expand dataset for production