gbyuvd
/

FastChemTokenizer

Feature Extraction

Model card Files Files and versions

gbyuvd commited on Sep 19, 2025

Commit

1113c2e

·

verified ·

1 Parent(s): d395cf2

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -56,7 +56,7 @@ Core's vocab length = 781 (after pruning)
 ✅ Even though 1.32x slower, it produces **2.65x lesser tokens**
 ✅ **~61x memory saving with tails** and **~25x** with core
-## 🧩 Vocabulary
 - **Final vocab size**: 1,238 tokens
 - **Includes**: 391 backbone motifs + 391 tail motifs + special tokens (`<s>`, `</s>`, `<pad>`, `<unk>`, `<mask>`)

 ✅ Even though 1.32x slower, it produces **2.65x lesser tokens**
 ✅ **~61x memory saving with tails** and **~25x** with core
+## 🧩 Vocabulary (SMILES)
 - **Final vocab size**: 1,238 tokens
 - **Includes**: 391 backbone motifs + 391 tail motifs + special tokens (`<s>`, `</s>`, `<pad>`, `<unk>`, `<mask>`)