Class VLLMConfig

camel/configs/vllm_config.py:25–108

r"""Defines the parameters for generating chat completions using the OpenAI API. Reference: https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html Args: temperature (float, optional): Sampling temperature to use, between :obj:`0` and :obj:`2`. Higher v

# flake8: noqa: E501
class VLLMConfig(BaseConfig):
    r"""Defines the parameters for generating chat completions using the
    OpenAI API.

    Reference: https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html

    Args:
        temperature (float, optional): Sampling temperature to use, between
            :obj:`0` and :obj:`2`. Higher values make the output more random,
            while lower values make it more focused and deterministic.
            (default: :obj:`0.2`)
        top_p (float, optional): An alternative to sampling with temperature,
            called nucleus sampling, where the model considers the results of
            the tokens with top_p probability mass. So :obj:`0.1` means only
            the tokens comprising the top 10% probability mass are considered.
            (default: :obj:`1.0`)
        n (int, optional): How many chat completion choices to generate for
            each input message. (default: :obj:`1`)
        response_format (object, optional): An object specifying the format
            that the model must output. Compatible with GPT-4 Turbo and all
            GPT-3.5 Turbo models newer than gpt-3.5-turbo-1106. Setting to
            {"type": "json_object"} enables JSON mode, which guarantees the
            message the model generates is valid JSON. Important: when using
            JSON mode, you must also instruct the model to produce JSON
            yourself via a system or user message. Without this, the model
            may generate an unending stream of whitespace until the generation
            reaches the token limit, resulting in a long-running and seemingly
            "stuck" request. Also note that the message content may be
            partially cut off if finish_reason="length", which indicates the
            generation exceeded max_tokens or the conversation exceeded the
            max context length.
        stream (bool, optional): If True, partial message deltas will be sent
            as data-only server-sent events as they become available.
            (default: :obj:`False`)
        stop (str or list, optional): Up to :obj:`4` sequences where the API
            will stop generating further tokens. (default: :obj:`None`)
        max_tokens (int, optional): The maximum number of tokens to generate
            in the chat completion. The total length of input tokens and
            generated tokens is limited by the model's context length.
            (default: :obj:`None`)
        presence_penalty (float, optional): Number between :obj:`-2.0` and
            :obj:`2.0`. Positive values penalize new tokens based on whether
            they appear in the text so far, increasing the model's likelihood
            to talk about new topics. See more information about frequency and
            presence penalties. (default: :obj:`0.0`)
        frequency_penalty (float, optional): Number between :obj:`-2.0` and
            :obj:`2.0`. Positive values penalize new tokens based on their
            existing frequency in the text so far, decreasing the model's
            likelihood to repeat the same line verbatim. See more information
            about frequency and presence penalties. (default: :obj:`0.0`)
        logit_bias (dict, optional): Modify the likelihood of specified tokens
            appearing in the completion. Accepts a json object that maps tokens
            (specified by their token ID in the tokenizer) to an associated
            bias value from :obj:`-100` to :obj:`100`. Mathematically, the bias
            is added to the logits generated by the model prior to sampling.
            The exact effect will vary per model, but values between:obj:` -1`
            and :obj:`1` should decrease or increase likelihood of selection;
            values like :obj:`-100` or :obj:`100` should result in a ban or