T5

T5 (Text-to-Text Transfer Transformer)는 모든 NLP 작업을 텍스트-투-텍스트 문제로 다루는 트랜스포머 기반 언어 모델입니다. 다양한 비지도 및 지도 학습 작업에서 사전 훈련되어 다양한 언어 작업에 매우 유연하게 적용될 수 있습니다. RBLN NPU는 Optimum RBLN을 사용하여 T5 모델 추론을 가속화할 수 있습니다.

API 참조

Classes

RBLNT5EncoderModel

Bases: RBLNTransformerEncoderForFeatureExtraction

The T5 Model transformer with an encoder-only architecture for feature extraction. This model inherits from [RBLNTransformerEncoderForFeatureExtraction]. Check the superclass documentation for the generic methods the library implements for all its models.

Important Note

This model supports various sizes of the T5EncoderModel. For optimal performance, it is highly recommended to adjust the tensor parallelism setting based on the model size. Please refer to the Optimum RBLN Overview for guidance on choosing the appropriate tensor parallelism size for your model.

Examples:

from optimum.rbln import RBLNT5EncoderModel

model = RBLNT5EncoderModel.from_pretrained(
    "sentence-transformers/sentence-t5-xxl",
    export=True,
    rbln_tensor_parallel_size=4,
)

model.save_pretrained("compiled-sentence-t5-xxl")

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., 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.

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., 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.

RBLNT5ForConditionalGeneration

Bases: RBLNModelForSeq2SeqLM

The T5 Model transformer with a language modeling head for conditional generation. This model inherits from [RBLNModelForSeq2SeqLM]. Check the superclass documentation for the generic methods the library implements for all its models.

Important Note

This model supports various sizes of the T5ForConditionalGeneration. For optimal performance, it is highly recommended to adjust the tensor parallelism setting based on the model size. Please refer to the Optimum RBLN Overview for guidance on choosing the appropriate tensor parallelism size for your model.

Examples:

from optimum.rbln import RBLNT5ForConditionalGeneration

model = RBLNT5ForConditionalGeneration.from_pretrained(
    "google-t5/t5-11b",
    export=True,
    rbln_tensor_parallel_size=4,
)

model.save_pretrained("compiled-sentence-t5-xxl")

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., 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.

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., 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.

Classes

RBLNT5EncoderModelConfig

Bases: RBLNTransformerEncoderForFeatureExtractionConfig

Configuration class for RBLNT5EncoderModel.

This configuration class stores the configuration parameters specific to RBLN-optimized T5 encoder models for feature extraction 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.

RBLNT5ForConditionalGenerationConfig

Bases: RBLNModelForSeq2SeqLMConfig

Configuration class for RBLNT5ForConditionalGeneration.

This configuration class stores the configuration parameters specific to RBLN-optimized T5 models for conditional text generation tasks.

Functions

__init__(batch_size=None, enc_max_seq_len=None, dec_max_seq_len=None, use_attention_mask=None, pad_token_id=None, kvcache_num_blocks=None, kvcache_block_size=None, **kwargs)

Parameters:

Name	Type	Description	Default
batch_size	Optional[int]	The batch size for inference. Defaults to 1.	None
enc_max_seq_len	Optional[int]	Maximum sequence length for the encoder.	None
dec_max_seq_len	Optional[int]	Maximum sequence length for the decoder.	None
use_attention_mask	Optional[bool]	Whether to use attention masks during inference.	None
pad_token_id	Optional[int]	The ID of the padding token in the vocabulary.	None
kvcache_num_blocks	Optional[int]	The total number of blocks to allocate for the PagedAttention KV cache for the SelfAttention. Defaults to batch_size.	None
kvcache_block_size	Optional[int]	Sets the size (in number of tokens) of each block in the PagedAttention KV cache for the SelfAttention. Defaults to dec_max_seq_len.	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.