XLM-RoBERTa

XLM-RoBERTa is a multilingual version of RoBERTa, trained on a large corpus of text in 100 different languages. It uses a shared vocabulary and model weights across all languages, allowing for cross-lingual transfer learning. This makes it particularly effective for multilingual NLP tasks and low-resource languages. RBLN NPUs can accelerate XLM-RoBERTa model inference using Optimum RBLN.

Key Classes

• RBLNXLMRobertaModel: XLM-RoBERTa base model implementation for feature extraction on RBLN NPU
• RBLNXLMRobertaModelConfig: Configuration class for XLM-RoBERTa base model
• RBLNXLMRobertaForSequenceClassification: XLM-RoBERTa model implementation for sequence classification tasks on RBLN NPU
• RBLNXLMRobertaForSequenceClassificationConfig: Configuration class for XLM-RoBERTa sequence classification model

API Reference

Classes

RBLNXLMRobertaModel

Bases: RBLNTransformerEncoderForFeatureExtraction

XLM-RoBERTa base model optimized for RBLN NPU.

Functions

from_pretrained(model_id, export=False, 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	Union[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	A boolean flag to indicate whether the model should be compiled.	False
rbln_config	Optional[Union[Dict, RBLNModelConfig]]	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	Dict[str, 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
Self	A RBLN model instance ready for inference on RBLN NPU devices.

from_model(model, *, rbln_config=None, **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	The PyTorch model to be compiled. The object must be an instance of the HuggingFace transformers PreTrainedModel class.	required
rbln_config	Optional[Union[Dict, RBLNModelConfig]]	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	Dict[str, 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
Self	A RBLN model instance ready for inference on RBLN NPU devices.

save_pretrained(save_directory)

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

Parameters:

Name	Type	Description	Default
save_directory	Union[str, PathLike]	The directory to save the model and its configuration files. Will be created if it doesn't exist.	required

RBLNXLMRobertaForSequenceClassification

Bases: RBLNModelForSequenceClassification

XLM-RoBERTa model for sequence classification tasks optimized for RBLN NPU.

Functions

from_pretrained(model_id, export=False, 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	Union[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	A boolean flag to indicate whether the model should be compiled.	False
rbln_config	Optional[Union[Dict, RBLNModelConfig]]	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	Dict[str, 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
Self	A RBLN model instance ready for inference on RBLN NPU devices.

from_model(model, *, rbln_config=None, **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	The PyTorch model to be compiled. The object must be an instance of the HuggingFace transformers PreTrainedModel class.	required
rbln_config	Optional[Union[Dict, RBLNModelConfig]]	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	Dict[str, 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
Self	A RBLN model instance ready for inference on RBLN NPU devices.

save_pretrained(save_directory)

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

Parameters:

Name	Type	Description	Default
save_directory	Union[str, PathLike]	The directory to save the model and its configuration files. Will be created if it doesn't exist.	required

Classes

RBLNXLMRobertaModelConfig

Bases: RBLNTransformerEncoderForFeatureExtractionConfig

Configuration class for XLM-RoBERTa model. Inherits from RBLNTransformerEncoderForFeatureExtractionConfig with no additional parameters.

Functions

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

Parameters:

Name	Type	Description	Default
max_seq_len	Optional[int]	Maximum sequence length supported by the model.	None
batch_size	Optional[int]	The batch size for inference. Defaults to 1.	None
model_input_names	Optional[List[str]]	Names of the input tensors for the model. Defaults to class-specific rbln_model_input_names if not provided.	None
**kwargs	Dict[str, Any]	Additional arguments passed to the parent RBLNModelConfig.	{}

Raises:

Type	Description
ValueError	If batch_size is not a positive integer.

RBLNXLMRobertaForSequenceClassificationConfig

Bases: RBLNModelForSequenceClassificationConfig

Configuration class for XLM-RoBERTa sequence classification model. Inherits from RBLNModelForSequenceClassificationConfig with no additional parameters.

Functions

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

Parameters:

Name	Type	Description	Default
max_seq_len	Optional[int]	Maximum sequence length supported by the model.	None
batch_size	Optional[int]	The batch size for inference. Defaults to 1.	None
model_input_names	Optional[List[str]]	Names of the input tensors for the model. Defaults to class-specific rbln_model_input_names if not provided.	None
**kwargs	Dict[str, Any]	Additional arguments passed to the parent RBLNModelConfig.	{}

Raises:

Type	Description
ValueError	If batch_size is not a positive integer.