Class AutoSeq2SeqLM

test/general/lm_eval/models/huggingface.py:564–720

Seq2Seq language modeling. You can find a set of supported models in the following documentation: https://huggingface.co/docs/transformers/main/model_doc/auto#transformers.AutoModelForSeq2SeqLM

class AutoSeq2SeqLM(HuggingFaceAutoLM):
    """Seq2Seq language modeling.
    You can find a set of supported models in the following documentation:
    https://huggingface.co/docs/transformers/main/model_doc/auto#transformers.AutoModelForSeq2SeqLM
    """

    AUTO_MODEL_CLASS = transformers.AutoModelForSeq2SeqLM
    AUTO_PEFT_CLASS = peft.PeftModel

    def loglikelihood(
        self, requests: List[Tuple[str, str]]
    ) -> List[Tuple[float, bool]]:
        new_requests = []
        for chunk in utils.chunks(requests, self.batch_size):
            context, continuation = zip(*chunk)

            # Fill empty contexts with the EOT token.
            context = [
                f"{self.eot_token}" if len(text) == 0 else text for text in context
            ]
            context_enc = self.tok_encode_batch(context)
            for key in context_enc:
                context_enc[key] = context_enc[key][:, -self.max_length :]

            # Remove leading whitespace introduced by the default
            # `text_target_separator` since the context and continuation
            # will not be concatenated as a single (decoder) input.
            continuation = [text.lstrip() for text in continuation]
            continuation_enc = self.tok_encode_batch(list(continuation))
            for key in continuation_enc:
                continuation_enc[key] = continuation_enc[key][:, -self.max_length :]

            new_requests.append(
                ((context, continuation), context_enc, continuation_enc)
            )
        return self._loglikelihood_tokens(new_requests)

    def loglikelihood_rolling(self, requests: List[Tuple[str, str]]) -> List[float]:
        loglikelihoods = []
        for (string,) in tqdm(requests):
            rolling_token_windows = list(
                map(
                    utils.make_disjoint_window,
                    utils.get_rolling_token_windows(
                        token_list=self.tok_encode(string),
                        prefix_token=self.eot_token_id,
                        max_seq_len=self.max_length,
                        context_len=1,
                    ),
                )
            )
            contexts, conts = utils.split_and_pad_windows(
                rolling_token_windows,
                pad_token_id=self.eot_token_id,
                max_seq_len=self.max_length,
            )
            # Manually create BatchEncoding tensors with attention masks as
            # expected by `self._model_call` in `self._loglikelihood_tokens`.