RoBERTa¶
RoBERTa (Robustly Optimized BERT Pretraining Approach)는 훈련 방법론과 데이터 변경을 통해 원래 모델을 개선한 BERT의 최적화 버전입니다. 다음 문장 예측 목표를 제거하고 더 큰 배치, 더 많은 데이터 및 동적 마스킹 패턴으로 훈련됩니다. RBLN NPU는 Optimum RBLN을 사용하여 RoBERTa 모델 추론을 가속화할 수 있습니다.
API 참조¶
Classes¶
RBLNRobertaForMaskedLM
¶
Bases: RBLNModelForMaskedLM
RBLN optimized RoBERTa model for masked language modeling tasks.
This class provides hardware-accelerated inference for RoBERTa models on RBLN devices, supporting masked language modeling tasks such as token prediction and text completion.
Functions¶
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
|
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
|
Optional[bool]
|
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
|
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., |
None
|
kwargs
|
Any
|
Additional keyword arguments. Arguments with the prefix |
{}
|
Returns:
Type | Description |
---|---|
RBLNModel
|
A RBLN model instance ready for inference on RBLN NPU devices. |
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
|
Union[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
|
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
|
The PyTorch model to be compiled. The object must be an instance of the HuggingFace transformers PreTrainedModel class. |
required |
config
|
Optional[PretrainedConfig]
|
The configuration object associated with the model. |
None
|
rbln_config
|
Optional[Union[RBLNModelConfig, Dict]]
|
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., |
None
|
kwargs
|
Any
|
Additional keyword arguments. Arguments with the prefix |
{}
|
The method performs the following steps:
- Compiles the PyTorch model into an optimized RBLN graph
- Configures the model for the specified NPU device
- Creates the necessary runtime objects if requested
- Saves the compiled model and configurations
Returns:
Type | Description |
---|---|
RBLNModel
|
A RBLN model instance ready for inference on RBLN NPU devices. |
RBLNRobertaForSequenceClassification
¶
Bases: RBLNModelForSequenceClassification
RBLN optimized RoBERTa model for sequence classification tasks.
This class provides hardware-accelerated inference for RoBERTa models on RBLN devices, supporting text classification tasks such as sentiment analysis, topic classification, and other sequence-level prediction tasks.
Functions¶
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
|
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
|
Optional[bool]
|
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
|
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., |
None
|
kwargs
|
Any
|
Additional keyword arguments. Arguments with the prefix |
{}
|
Returns:
Type | Description |
---|---|
RBLNModel
|
A RBLN model instance ready for inference on RBLN NPU devices. |
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
|
Union[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
|
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
|
The PyTorch model to be compiled. The object must be an instance of the HuggingFace transformers PreTrainedModel class. |
required |
config
|
Optional[PretrainedConfig]
|
The configuration object associated with the model. |
None
|
rbln_config
|
Optional[Union[RBLNModelConfig, Dict]]
|
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., |
None
|
kwargs
|
Any
|
Additional keyword arguments. Arguments with the prefix |
{}
|
The method performs the following steps:
- Compiles the PyTorch model into an optimized RBLN graph
- Configures the model for the specified NPU device
- Creates the necessary runtime objects if requested
- Saves the compiled model and configurations
Returns:
Type | Description |
---|---|
RBLNModel
|
A RBLN model instance ready for inference on RBLN NPU devices. |
Classes¶
RBLNRobertaForMaskedLMConfig
¶
Bases: RBLNModelForMaskedLMConfig
Configuration class for RBLNRobertaForMaskedLM.
This configuration class stores the configuration parameters specific to RBLN-optimized RoBERTa models for masked language modeling tasks.
Functions¶
__init__(max_seq_len=None, batch_size=None, model_input_names=None, model_input_shapes=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
|
Any
|
Additional arguments passed to the parent RBLNModelConfig. |
{}
|
Raises:
Type | Description |
---|---|
ValueError
|
If batch_size is not a positive integer. |
load(path, **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 |
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 |
RBLNModelConfig
|
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.
RBLNRobertaForSequenceClassificationConfig
¶
Bases: RBLNModelForSequenceClassificationConfig
Configuration class for RBLNRobertaForSequenceClassification.
This configuration class stores the configuration parameters specific to RBLN-optimized RoBERTa models for sequence classification tasks.
Functions¶
__init__(max_seq_len=None, batch_size=None, model_input_names=None, model_input_shapes=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
|
Any
|
Additional arguments passed to the parent RBLNModelConfig. |
{}
|
Raises:
Type | Description |
---|---|
ValueError
|
If batch_size is not a positive integer. |
load(path, **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 |
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 |
RBLNModelConfig
|
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.