Update README.md

README.md

@@ -19,6 +19,18 @@ library_name: transformers
 
 The **i3 Model** is a memory-optimized language model designed for conversational understanding. This version uses streaming tokenization to minimize RAM usage during training.
 
+## Use
+```py
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="FlameF0X/i3-12m")
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+pipe(messages)
+```
+
 ## Model Statistics
 
 - **Vocabulary Size**: 4,466 (variable-length chunks)