Normalize, concatenate, and project Kimi patch features

Read the equation

Per-patch LayerNorm is applied before adjacent patch features are concatenated by the reshape. The projection network then maps each merged group into the language representation. With the displayed configuration, the concatenated input width is 4,608 and the final output width is 7,168; the batch dimension B is retained.

Terms & definitions

The recovered passage does not supply a separate symbol table. Read the source context for the notation used in this version; familiar letters may carry different meanings in other builds.

How it works

Read the definition from its right-hand expression to the quantity on the left. Its surrounding source records the intended input, state, or parameter context. Where the source leaves an operation unspecified, this page preserves that gap.

Assumptions & limits

Source recovery establishes that the expression appears in this record. Its mathematical validity, implementation behavior, and interpretation must be assessed separately. See the linked source and research notes for the checks available for this version.

Original context

else:
            # B, N, N_k, C = x.shape
            B = x.shape[0]
            x = self.proj(self.pre_norm(x).view(B, -1, self.hidden_size))
        return x

x = self.proj(self.pre_norm(x).view(B, -1, self.hidden_size))

Related builds