Skip to content

DistilBERT

DistilBERT is a smaller, faster, and lighter version of BERT created using knowledge distillation. This model is particularly useful for applications with resource constraints. RBLN NPUs can accelerate DistilBERT model inference using RBLN Optimum.

API Reference

RBLNDistilBertForQuestionAnswering

Bases: RBLNModelForQuestionAnswering

RBLN optimized DistilBERT model for question answering tasks.

This class provides hardware-accelerated inference for DistilBERT models on RBLN devices, supporting extractive question answering tasks where the model predicts start and end positions of answers in text.

forward(input_ids=None, attention_mask=None, **kwargs)

Forward pass for the RBLN-optimized DistilBERT model for question answering tasks.

Parameters:

Name Type Description Default
input_ids torch.Tensor of shape (batch_size, sequence_length)

Indices of input sequence tokens in the vocabulary.

 None
attention_mask torch.Tensor of shape (batch_size, sequence_length)

Mask to avoid performing attention on padding token indices.

 None

Returns:

Type Description
tuple | QuestionAnsweringModelOutput

The model outputs. If return_dict=False is passed, returns a tuple of tensors. Otherwise, returns a QuestionAnsweringModelOutput object.

from_model(model, config=None, rbln_config=None, model_save_dir=None, subfolder='', **kwargs) classmethod

Converts and compiles a pre-trained HuggingFace library model into a RBLN model. This method performs the actual model conversion and compilation process.

Parameters:

Name Type Description Default
model PreTrainedModel | ModelMixin

The PyTorch model to be compiled. The object must be a HuggingFace transformers PreTrainedModel or a Diffusers component based on diffusers.ModelMixin, such as a VAE, UNet or ControlNet.

 required
config PretrainedConfig | None

The configuration object associated with the model.

 None
rbln_config RBLNModelConfig | dict | None

Configuration for RBLN model compilation and runtime. This can be provided as a dictionary or an instance of the model's configuration class (e.g., RBLNLlamaForCausalLMConfig for Llama models). For detailed configuration options, see the specific model's configuration class documentation.

 None
kwargs Any

Additional keyword arguments. Arguments with the prefix rbln_ are passed to rbln_config, while the remaining arguments are passed to the HuggingFace library.

 {}

The method performs the following steps:

  1. Compiles the PyTorch model into an optimized RBLN graph
  2. Configures the model for the specified NPU device
  3. Creates the necessary runtime objects if requested
  4. Saves the compiled model and configurations

Returns:

Type Description
RBLNModel

A RBLN model instance ready for inference on RBLN NPU devices.

from_pretrained(model_id, export=None, rbln_config=None, **kwargs) classmethod

The from_pretrained() function is utilized in its standard form as in the HuggingFace transformers library. User can use this function to load a pre-trained model from the HuggingFace library and convert it to a RBLN model to be run on RBLN NPUs.

Parameters:

Name Type Description Default
model_id str | Path

The model id of the pre-trained model to be loaded. It can be downloaded from the HuggingFace model hub or a local path, or a model id of a compiled model using the RBLN Compiler.

 required
export bool | None

A boolean flag to indicate whether the model should be compiled. If None, it will be determined based on the existence of the compiled model files in the model_id.

 None
rbln_config dict | RBLNModelConfig | None

Configuration for RBLN model compilation and runtime. This can be provided as a dictionary or an instance of the model's configuration class (e.g., RBLNLlamaForCausalLMConfig for Llama models). For detailed configuration options, see the specific model's configuration class documentation.

 None
kwargs Any

Additional keyword arguments. Arguments with the prefix rbln_ are passed to rbln_config, while the remaining arguments are passed to the HuggingFace library.

 {}

Returns:

Type Description
RBLNModel

A RBLN model instance ready for inference on RBLN NPU devices.

get_hf_class() classmethod

Lazily load and cache the HuggingFace class this model wraps.

The class is looked up in hf_library_name under the name without the RBLN prefix (e.g. RBLNLlamaForCausalLM -> LlamaForCausalLM).

save_pretrained(save_directory, push_to_hub=False, **kwargs)

Saves a model and its configuration file to a directory, so that it can be re-loaded using the [~optimum.rbln.modeling_base.RBLNBaseModel.from_pretrained] class method.

Parameters:

Name Type Description Default
save_directory str | Path

Directory where to save the model file.

 required
push_to_hub bool

Whether or not to push your model to the HuggingFace model hub after saving it.

 False

RBLNDistilBertForQuestionAnsweringConfig

Bases: RBLNModelForQuestionAnsweringConfig

Configuration class for RBLNDistilBertForQuestionAnswering.

This configuration class stores the configuration parameters specific to RBLN-optimized DistilBERT models for question answering tasks.

initialize_submodule_config(submodule_config=None, force_kwargs=False, **kwargs)

Build the config of a submodule from the parent's runtime options and kwargs.

Returns the submodule config instance when its class is known (an instance was passed, or cls_name was given), otherwise the merged kwargs dict for the model class to resolve later.

__init__(max_seq_len=None, batch_size=None, model_input_names=None, **kwargs)

Parameters:

Name Type Description Default
max_seq_len int | list[int] | None

Maximum sequence length supported by the model. A single integer compiles the model for one sequence length. A list of integers enables sequence-length bucketing: the model is compiled for each length on the default [batch_size, max_seq_len] input layout and, at inference time, the runtime dispatches to the smallest bucket that fits each input.

 None
batch_size int | None

The batch size for inference. Defaults to 1.

 None
model_input_names list[str] | None

Names of the input tensors for the model. Defaults to class-specific rbln_model_input_names if not provided.

 None
kwargs Any

Additional arguments passed to the parent RBLNModelConfig.

 {}

Raises:

Type Description
ValueError

If batch_size is not a positive integer.

get_load_overrides()

Extract the options that must cross the load boundary, for passing to from_pretrained.

Returns the explicitly-set runtime options (device, device_map, create_runtimes, activate_profiler, timeout) and the subclass-specific non-save attributes (load-behavior flags such as _load_visual_runtime, which are never serialized so they can only travel with the caller), recursively including submodules. Compile-time attributes are not included: when loading a compiled model they come from the artifact's rbln_config.json, and this dict is merged on top of it.

Returns:

Type Description
dict[str, Any]

Dictionary of load overrides, keyed like the rbln_config dict accepted by from_pretrained.

from_pretrained(path, rbln_config=None, return_unused_kwargs=False, **kwargs) classmethod

Load a RBLNModelConfig from a path.

Parameters:

Name Type Description Default
path str

Path to the RBLNModelConfig file or directory containing the config file.

 required
rbln_config dict[str, Any] | None

Additional configuration to override.

 None
return_unused_kwargs bool

Whether to return unused kwargs.

 False
kwargs Any

Additional keyword arguments to override configuration values. Keys starting with 'rbln_' will have the prefix removed and be used to update the configuration.

 {}

Returns:

Name Type Description
RBLNModelConfig Self | tuple[Self, dict[str, Any]]

The loaded configuration instance.
Note

This method loads the configuration from the specified path and applies any provided overrides. If the loaded configuration class doesn't match the expected class, a warning will be logged.

Examples:

1
config = RBLNResNetForImageClassificationConfig.from_pretrained("/path/to/model")