How to instantiate a BaseModelBackend class with local LLM

[Handsomeliuxzh]

class BaseModelBackend(ABC, metaclass=ModelBackendMeta):
r"""Base class for different model backends.
It may be OpenAI API, a local LLM, a stub for unit tests, etc.

Args:
    model_type (Union[ModelType, str]): Model for which a backend is
        created.
    model_config_dict (Optional[Dict[str, Any]], optional): A config
        dictionary. (default: :obj:`{}`)
    api_key (Optional[str], optional): The API key for authenticating
        with the model service. (default: :obj:`None`)
    url (Optional[str], optional): The url to the model service.
        (default: :obj:`None`)
    token_counter (Optional[BaseTokenCounter], optional): Token
        counter to use for the model. If not provided,
        :obj:`OpenAITokenCounter` will be used. (default: :obj:`None`)
"""

def __init__(
    self,
    model_type: Union[ModelType, str],
    model_config_dict: Optional[Dict[str, Any]] = None,
    api_key: Optional[str] = None,
    url: Optional[str] = None,
    token_counter: Optional[BaseTokenCounter] = None,
) -> None:
    self.model_type: UnifiedModelType = UnifiedModelType(model_type)
    if model_config_dict is None:
        model_config_dict = {}
    self.model_config_dict = model_config_dict
    self._api_key = api_key
    self._url = url
    self._token_counter = token_counter
    self.check_model_config()

[Wendong-Fan]

Hey @Handsomeliuxzh , here is our documentation: https://docs.camel-ai.org/key_modules/models.html#using-on-device-open-source-models

[Handsomeliuxzh]

Thanks! By the way, can I instantiate a ChatAgent with local huggingface models (safetensors type) ?

[Wendong-Fan]

it's not supported yet, but you could call gguf models via ollama