Update README.md

README.md

@@ -40,9 +40,7 @@ Sol Nano is a 2,895,188-parameter language model trained on 5 billion tokens. It
 | Optimizer updates | 19,074 |
 | Weights | FP32 safetensors |
 
-The blocks use causal grouped-query attention, RoPE, QK normalization, and loop conditioning. Token embeddings share weights with the output head. TN-Gram provides factorized local memory for orders 2-5. XSA and Engram are disabled.
-
-Attention runs through compiled Triton FlexAttention. The backend does not use PyTorch SDPA.
+The blocks use causal grouped-query attention, RoPE, QK normalization, and loop conditioning. Token embeddings share weights with the output head. TN-Gram provides factorized local memory for orders 2-5.
 
 ## Use