Update README.md

README.md

@@ -58,11 +58,8 @@ CLSS is trained with a **CLIP-style contrastive objective**, aligning:
 
 This Hugging Face repository contains multiple PyTorch Lightning checkpoints, differing only in **embedding dimensionality**:
 
-- `h8_r10.lckpt`   → 8-dimensional embeddings  
-- `h16_r10.lckpt`  → 16-dimensional embeddings  
-- `h32_r10.lckpt`  → 32-dimensional embeddings (paper default)  
-- `h64_r10.lckpt`  → 64-dimensional embeddings  
-- `h128_r10.lckpt` → 128-dimensional embeddings  
+- `CLSS-full.lckpt` → Trained exclusively on full sequences
+- `CLSS-sub.lckpt`  → Trained with subsequences  
 
 ---