load_model

probly.representer.sampler.huggingface.load_model(model_name: str, *, cache_dir: str | PathLike[str] | None = None, force_download: bool = False, model_kwargs: Mapping[str, object] | None = None, tokenizer_kwargs: Mapping[str, object] | None = None) → tuple[GenerativePreTrainedModel, PreTrainedTokenizerBase][source]

Load a Hugging Face causal language model and tokenizer for sampling.

Parameters:

  • model_name – Hugging Face model name or local model path.

  • cache_dir – Optional Hugging Face cache directory.

  • force_download – Whether Hugging Face should re-download files even if cached.

  • model_kwargs – Additional keyword arguments forwarded to AutoModelForCausalLM.from_pretrained.

  • tokenizer_kwargs – Additional keyword arguments forwarded to AutoTokenizer.from_pretrained.

Returns:

The loaded model and tokenizer.