KimiK25ForConditionalGeneration.prepare_inputs_for_generation: attention mask

Read the equation

In KimiK25ForConditionalGeneration.prepare_inputs_for_generation, this statement defines or updates attention_mask. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.

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 attention_mask 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

# If the cache has seen more tokens than it can hold, then the cache has a size limit. Let's discard the
            # older attention values, as their corresponding values are not part of the input.
            if cache_length < past_length and attention_mask is not None:
                attention_mask = attention_mask[:, -(cache_length +
                                                     input_ids.shape[1]):]

        position_ids = kwargs.get("position_ids", None)
        if attention_mask is not None and position_ids is None:

attention_mask = attention_mask[:, -(cache_length +
                                                     input_ids.shape[1]):]

Related builds