Update README.md

README.md

@@ -5,6 +5,7 @@ base_model:
 ---
 
 # Model Overview
+
 This model is a multilingual Named Entity Recognition (NER) transformer designed for name 
 and address entity extraction with Malaysian context.
 
@@ -18,11 +19,13 @@ The model is built on top of Qwen3(Qwen3-0.6B) and uses a custom non-causal atte
 mechanism.
 
 ## Predicted Classes
+
 - 0 : Non-entity token
 - 1 : Name entity
 - 2 : Address entity
 
 ## Transformer Inference Example
+
 ```python
 from transformers import AutoTokenizer, Qwen3ForTokenClassification, AttentionInterface
 from typing import Optional
@@ -106,4 +109,9 @@ with toch.no_grad():
 ```
 
 ## Evaluation Result
-- F1 macro: 0.81
+
+- F1 macro: 0.81
+
+## Optimized inference
+
+We build small dynamic batching library for this, https://github.com/Scicom-AI-Enterprise-Organization/entity-api