src/lighteval/models/sglang/sglang_model.py [209:239]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        tokenizer.pad_token = tokenizer.eos_token
        return tokenizer

    def greedy_until(
        self,
        docs: list[Doc],
    ) -> list[ModelResponse]:
        """
        Generates responses using a greedy decoding strategy until certain ending conditions are met.

        Args:
            requests (list[Request]): list of requests containing the context and ending conditions.
            override_bs (int, optional): Override the batch size for generation. Defaults to None.

        Returns:
            list[GenerateReturn]: list of generated responses.
        """
        dataset = GenerativeTaskDataset(requests=docs, num_dataset_splits=self.DATASET_SPLITS)
        results = []

        for split in tqdm(
            dataset.splits_iterator(),
            total=dataset.num_dataset_splits,
            desc="Splits",
            position=0,
            disable=False,
        ):
            if self.use_chat_template:
                stop_tokens = []
            else:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/lighteval/models/vllm/vllm_model.py [282:313]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        tokenizer.pad_token = tokenizer.eos_token
        return tokenizer

    def greedy_until(
        self,
        docs: list[Doc],
    ) -> list[ModelResponse]:
        """
        Generates responses using a greedy decoding strategy until certain ending conditions are met.

        Args:
            requests (list[Request]): list of requests containing the context and ending conditions.
            override_bs (int, optional): Override the batch size for generation. Defaults to None.

        Returns:
            list[GenerateReturn]: list of generated responses.
        """
        dataset = GenerativeTaskDataset(requests=docs, num_dataset_splits=self.DATASET_SPLITS)
        results = []

        for split in tqdm(
            dataset.splits_iterator(),
            total=dataset.num_dataset_splits,
            desc="Splits",
            position=0,
            disable=False,  # self.disable_tqdm,
        ):
            # For chat models, generation stops with EOS token, so we don't need to specify stop tokens
            if self.use_chat_template:
                stop_tokens = []
            else:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -