Sampling API

class taco_llm.SamplingParams(
    n: int = 1,
    best_of: Optional[int] = None,
    presence_penalty: float = 0.0,
    frequency_penalty: float = 0.0,
    repetition_penalty: float = 1.0,
    temperature: float = 1.0,
    top_p: float = 1.0,
    top_k: int = -1,
    min_p: float = 0.0,
    seed: Optional[int] = None,
    use_beam_search: bool = False,
    length_penalty: float = 1.0,
    early_stopping: Union[bool, str] = False,
    stop: Optional[Union[str, List[str]]] = None,
    stop_token_ids: Optional[List[int]] = None,
    ignore_eos: bool = False,
    max_tokens: Optional[int] = 16,
    min_tokens: int = 0,
    logprobs: Optional[int] = None,
    prompt_logprobs: Optional[int] = None,
    detokenize: bool = True,
    skip_special_tokens: bool = True,
    spaces_between_special_tokens: bool = True,
    logits_processors: Optional[Any] = None,
    include_stop_str_in_output: bool = False,
    truncate_prompt_tokens: Optional[Annotated[int, msgspec.Meta(ge=1)]] = None,
    no_repeat_ngram_size: int = 0
)
    """Sampling parameters for text generation.

    Overall, we follow the sampling parameters from the OpenAI text completion
    API (https://platform.openai.com/docs/api-reference/completions/create).
    In addition, we support beam search, which is not supported by OpenAI.
    
    Args:
        n: Number of output sequences to return for the given prompt.
        best_of: Number of output sequences that are generated from the prompt.
            From these `best_of` sequences, the top `n` sequences are returned.
            `best_of` must be greater than or equal to `n`. This is treated as
            the beam width when `use_beam_search` is True. By default, `best_of`
            is set to `n`.
        presence_penalty: Float that penalizes new tokens based on whether they
            appear in the generated text so far. Values > 0 encourage the model
            to use new tokens, while values < 0 encourage the model to repeat
            tokens.
        frequency_penalty: Float that penalizes new tokens based on their
            frequency in the generated text so far. Values > 0 encourage the
            model to use new tokens, while values < 0 encourage the model to
            repeat tokens.
        repetition_penalty: Float that penalizes new tokens based on whether
            they appear in the prompt and the generated text so far. Values > 1
            encourage the model to use new tokens, while values < 1 encourage
            the model to repeat tokens.
        temperature: Float that controls the randomness of the sampling. Lower
            values make the model more deterministic, while higher values make
            the model more random. Zero means greedy sampling.
        top_p: Float that controls the cumulative probability of the top tokens
            to consider. Must be in (0, 1]. Set to 1 to consider all tokens.
        top_k: Integer that controls the number of top tokens to consider. Set
            to -1 to consider all tokens.
        min_p: Float that represents the minimum probability for a token to be
            considered, relative to the probability of the most likely token.
            Must be in [0, 1]. Set to 0 to disable this.
        seed: Random seed to use for the generation.
        use_beam_search: Whether to use beam search instead of sampling.
        length_penalty: Float that penalizes sequences based on their length.
            Used in beam search.
        early_stopping: Controls the stopping condition for beam search. It
            accepts the following values: `True`, where the generation stops as
            soon as there are `best_of` complete candidates; `False`, where an
            heuristic is applied and the generation stops when is it very
            unlikely to find better candidates; `"never"`, where the beam search
            procedure only stops when there cannot be better candidates
            (canonical beam search algorithm).
        stop: List of strings that stop the generation when they are generated.
            The returned output will not contain the stop strings.
        stop_token_ids: List of tokens that stop the generation when they are
            generated. The returned output will contain the stop tokens unless
            the stop tokens are special tokens.
        include_stop_str_in_output: Whether to include the stop strings in
            output text. Defaults to False.
        ignore_eos: Whether to ignore the EOS token and continue generating
            tokens after the EOS token is generated.
        max_tokens: Maximum number of tokens to generate per output sequence.
        min_tokens: Minimum number of tokens to generate per output sequence
            before EOS or stop_token_ids can be generated
        logprobs: Number of log probabilities to return per output token.
            When set to None, no probability is returned. If set to a non-None
            value, the result includes the log probabilities of the specified
            number of most likely tokens, as well as the chosen tokens.
            Note that the implementation follows the OpenAI API: The API will
            always return the log probability of the sampled token, so there
            may be up to `logprobs+1` elements in the response.
        prompt_logprobs: Number of log probabilities to return per prompt token.
        detokenize: Whether to detokenize the output. Defaults to True.
        skip_special_tokens: Whether to skip special tokens in the output.
        spaces_between_special_tokens: Whether to add spaces between special
            tokens in the output.  Defaults to True.
        logits_processors: List of functions that modify logits based on
            previously generated tokens, and optionally prompt tokens as
            a first argument.
        truncate_prompt_tokens: If set to an integer k, will use only the last k
            tokens from the prompt (i.e., left truncation). Defaults to None
            (i.e., no truncation).
        no_repeat_ngram_size:
            If set to int > 0, all ngrams of that size can only occur once.
    """

no_repeat_ngram_size:
            If set to int > 0, all ngrams of that size can only occur once.