KimiK25ForConditionalGeneration.forward: extended attention mask[new batch index, new non attended tokens]

Read the equation

In KimiK25ForConditionalGeneration.forward, this statement defines or updates extended_attention_mask[new_batch_index, new_non_attended_tokens]. This statement fixes a numeric parameter or initializes a numerical state in this source version; it is not a separate governing law.

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

1. Read extended_attention_mask[new_batch_index, new_non_a as the quantity being defined or updated by this relation.

2. Substitute the source-defined variables or recorded values and follow the displayed arithmetic and indexing exactly.

3. Use this version’s variable definitions and update order. The same symbol may be assigned a different meaning in another build.

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

new_non_attended_tokens = non_attended_tokens[valid_indices]

                # Zero-out the places where we don't need to attend
                extended_attention_mask[new_batch_index,
                                        new_non_attended_tokens] = 0

                attention_mask = torch.cat(
                    (extended_attention_mask, attention_mask[:,

extended_attention_mask[new_batch_index,
                                        new_non_attended_tokens] = 0

Related builds