XLM-RoBERTa

XLM-RoBERTa는 100개 이상의 다양한 언어로 된 대규모 텍스트 코퍼스에서 훈련된 RoBERTa의 다국어 버전입니다. 모든 언어에 대해 공유된 어휘와 모델 가중치를 사용하여 언어 간 전이 학습을 가능하게 합니다. 이는 다국어 NLP 작업과 저자원 언어에 특히 효과적입니다. RBLN NPU는 Optimum RBLN을 사용하여 XLM-RoBERTa 모델 추론을 가속화할 수 있습니다.

주요 클래스

• RBLNXLMRobertaModel: RBLN NPU에서 특징 추출을 위한 XLM-RoBERTa 기본 모델 구현
• RBLNXLMRobertaModelConfig: XLM-RoBERTa 기본 모델의 설정 클래스
• RBLNXLMRobertaForSequenceClassification: RBLN NPU에서 시퀀스 분류 작업을 위한 XLM-RoBERTa 모델 구현
• RBLNXLMRobertaForSequenceClassificationConfig: XLM-RoBERTa 시퀀스 분류 모델의 설정 클래스

API 참조

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.