fix the calculation of act params

README_WEIGHTS.md

@@ -18,7 +18,7 @@ The DeepSeek-V3 weight file consists of two main components: **Main Model Weight
   - Input/output embedding layers and a complete set of 61 Transformer hidden layers.
 - **Parameter Count**:
   - Total parameters: **671B**
-  - Activation parameters: **36.7B** (including 0.9B for Embedding and 0.9B for the output Head).
+  - Activation parameters: **36.6B**.
 
 #### Structural Details