MinimaxCommon

class langchain_community.llms.minimax.MinimaxCommon

Bases: BaseModel

Common parameters for Minimax large language models.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

param max_tokens: int = 256

Denotes the number of tokens to predict per generation.

param minimax_api_host: str | None = None

param minimax_api_key: SecretStr | None = None

param minimax_group_id: str | None = None

param model: str = 'abab5.5-chat'

Model name to use.

param model_kwargs: Dict[str, Any] [Optional]

Holds any model parameters valid for create call not explicitly specified.

param temperature: float = 0.7

A non-negative float that tunes the degree of randomness in generation.

param top_p: float = 0.95

Total probability mass of tokens to consider at each step.

classmethod validate_environment(values: Dict) → Dict

Validate that api key and python package exists in environment.

Parameters:

values (Dict)

Return type:

Dict