Update README.md

README.md

@@ -49,10 +49,10 @@ Trained on ~2.7M valid SMILES built and curated from ChemBL34 (Zdrazil _et al._
 
 ## 🛠️ Implementation
 
-- **Algorithm**: Trie-based longest-prefix-match (no regex, no BPE)
+- **Algorithm**: Trie-based longest-prefix-match 
 - **Caching**: `@lru_cache` for repeated string encoding
 - **HF Compatible**: Implements `__call__`, `encode_plus`, `batch_encode_plus`, `save_pretrained`, `from_pretrained`
-- **Memory Efficient**: No token set — pure trie traversal
+- **Memory Efficient**: Trie traversal and cache
 
 ```python
 from FastChemTokenizer import FastChemTokenizer
@@ -175,4 +175,4 @@ Apache 2.0
   pages = {D654-D659},
   doi = {10.1093/nar/gkac1008}
 }
-```
+```