Update README.md

README.md

@@ -42,11 +42,11 @@ q = engine.encode("雪鴞好可愛")
 ```
 
 Files
-data/L1_base_embeddings.npy : embedding table (float32, V×1024)
-data/L1_base_vocab.json : vocab aligned with rows
-data/delta_base_scalar.npy : scalar bias (float32, V)
-engine.py : minimal runtime
-quickstart.py : example script
+- data/L1_base_embeddings.npy : embedding table (float32, V×1024)
+- data/L1_base_vocab.json : vocab aligned with rows
+- data/delta_base_scalar.npy : scalar bias (float32, V)
+- engine.py : minimal runtime
+- quickstart.py : example script
 
 Notes
 No safetensors / pytorch_model.bin is included because this model is distributed as a static NumPy embedding field.
@@ -55,9 +55,9 @@ No safetensors / pytorch_model.bin is included because this model is distributed
 
 ## Stress Test Results (Hard Retrieval Setting)
 
-corpus size = 1200
-eval size = 200
-ood ratio = 0.28
+- corpus size = 1200
+- eval size = 200
+- ood ratio = 0.28
 
 | Model | in-domain MRR@10 | OOD MRR@10 |
 |--------|-----------------|------------|