DeepSeek ForSequenceClassification.forward: sequence lengths

Read the equation

In DeepseekV3ForSequenceClassification.forward, this statement defines or updates sequence_lengths. 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 sequence_lengths as the quantity being defined or updated by this relation.

2. Chooses an argument maximizing the displayed objective over the stated feasible set.

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

sequence_lengths = -1
        else:
            if input_ids is not None:
                sequence_lengths = (torch.eq(
                    input_ids, self.config.pad_token_id).int().argmax(-1) -
                                    1).to(logits.device)
            else:
                sequence_lengths = -1

sequence_lengths = (torch.eq(
                    input_ids, self.config.pad_token_id).int().argmax(-1) -
                                    1).to(logits.device)

Related builds