BLIP-2

BLIP-2 모델은 이미지와 텍스트 입력을 모두 처리할 수 있는 멀티모달 모델입니다. 주로 시각적 질의응답(Visual Question Answering)이나 이미지 캡셔닝과 같은 작업에 사용됩니다. RBLN NPU는 Optimum RBLN을 사용하여 BLIP-2 모델 추론을 가속화할 수 있습니다.

API Reference

Classes

RBLNBlip2VisionModel

Bases: RBLNModel

RBLN optimized BLIP-2 vision encoder model.

This class provides hardware-accelerated inference for BLIP-2 vision encoders on RBLN devices, supporting image encoding for multimodal vision-language tasks.

Functions

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.

forward(pixel_values, interpolate_pos_encoding=False, return_dict=None)

Forward pass for the RBLN-optimized Blip2VisionModel model.

Parameters:

Name	Type	Description	Default
pixel_values	torch.FloatTensor of shape (batch_size, num_channels, height, width)	The tensors corresponding to the input images.	required
interpolate_pos_encoding	bool	Whether to interpolate the positional encoding of the image embeddings. Defaults to False.	False
return_dict	bool	Whether to return a ModelOutput instead of a plain tuple.	None

Returns:

Type	Description
Union[Tuple, BaseModelOutputWithPooling]	BaseModelOutputWithPooling or tuple(torch.FloatTensor): The model outputs. If return_dict=False is passed, returns a tuple of tensors. Otherwise, returns a BaseModelOutputWithPooling object.

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

RBLNBlip2QFormerModel

Bases: RBLNModel

RBLN optimized BLIP-2 Q-Former model.

This class provides hardware-accelerated inference for BLIP-2 Q-Former models on RBLN devices, which bridge vision and language modalities through cross-attention mechanisms for multimodal understanding tasks.

Functions

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.

forward(query_embeds, encoder_hidden_states=None, encoder_attention_mask=None, return_dict=None)

The forward pass for the RBLN-optimized Blip2QFormerModel model.

Parameters:

Name	Type	Description	Default
query_embeds	FloatTensor	Hidden states to be used in the attention computation.	required
encoder_hidden_states	FloatTensor	Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.	None
encoder_attention_mask	FloatTensor	Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder.	None
return_dict	bool	Whether to return a ModelOutput instead of a plain tuple.	None

Returns:

Type	Description
Union[Tuple[Tensor], BaseModelOutputWithPoolingAndCrossAttentions]	BaseModelOutputWithPoolingAndCrossAttentions or tuple(torch.FloatTensor): The model outputs. If return_dict=False is passed, returns a tuple of tensors. Otherwise, returns a BaseModelOutputWithPoolingAndCrossAttentions object.

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

RBLNBlip2ForConditionalGeneration

Bases: RBLNModel, RBLNDecoderOnlyGenerationMixin

RBLNBlip2ForConditionalGeneration is a multi-modal model that integrates vision and language processing capabilities, optimized for RBLN NPUs. It is designed for conditional generation tasks that involve both image and text inputs.

This model inherits from [RBLNModel]. Check the superclass documentation for the generic methods the library implements for all its models.

Important Note

This model includes a Large Language Model (LLM) as a submodule. For optimal performance, it is highly recommended to use tensor parallelism for the language model. This can be achieved by using the rbln_config parameter in the from_pretrained method. Refer to the from_pretrained documentation and the RBLNBlip2ForConditionalGeneration class for details.

Examples:

from optimum.rbln import RBLNBlip2ForConditionalGeneration

model = RBLNBlip2ForConditionalGeneration.from_pretrained(
    "Salesforce/blip2-opt-2.7b",
    export=True,
    rbln_config={
        "language_model": {
            "batch_size": 1,
            "max_seq_len": 2048,
            "tensor_parallel_size": 1,
            "use_inputs_embeds": True,
        },
    },
)

model.save_pretrained("compiled-blip2-opt-2.7b")

Functions

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.

generate(pixel_values, input_ids=None, attention_mask=None, inputs_embeds=None, interpolate_pos_encoding=False, **generate_kwargs)

The generate function is utilized in its standard form as in the HuggingFace transformers library. User can use this function to generate text from the model. Check the HuggingFace transformers documentation for more details.

Parameters:

Name	Type	Description	Default
pixel_values	FloatTensor	Input images to be processed.	required
input_ids	LongTensor	The sequence used as a prompt for the generation.	None
attention_mask	LongTensor	Mask to avoid performing attention on padding token indices	None
inputs_embeds	FloatTensor	Embedded representation of the inputs. Should be float, not int tokens.	None

Returns: A list of strings of length batch_size * num_captions.

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

Classes

RBLNBlip2VisionModelConfig

Bases: RBLNModelConfig

Configuration class for RBLNBlip2VisionModel.

This configuration class stores the configuration parameters specific to RBLN-optimized BLIP-2 vision encoder models for multimodal tasks.

Functions

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.

RBLNBlip2QFormerModelConfig

Bases: RBLNModelConfig

Configuration class for RBLNBlip2QFormerModel.

This configuration class stores the configuration parameters specific to RBLN-optimized BLIP-2 Q-Former models that bridge vision and language modalities.

Functions

__init__(batch_size=None, num_query_tokens=None, image_text_hidden_size=None, **kwargs)

Parameters:

Name	Type	Description	Default
num_query_tokens	Optional[int]	The number of query tokens passed through the Transformer.	None
image_text_hidden_size	Optional[int]	Dimensionality of the hidden state of the image-text fusion layer.	None
kwargs		Additional arguments passed to the parent RBLNModelConfig.	{}

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.

RBLNBlip2ForConditionalGenerationConfig

Bases: RBLNModelConfig

Configuration class for RBLNBlip2ForConditionalGeneration.

This configuration class stores the configuration parameters specific to RBLN-optimized BLIP-2 models for conditional generation tasks that involve both image and text inputs.

Functions

__init__(batch_size=None, vision_model=None, qformer=None, language_model=None, **kwargs)

Parameters:

Name	Type	Description	Default
batch_size	Optional[int]	The batch size for inference. Defaults to 1.	None
vision_model	Optional[RBLNModelConfig]	Configuration for the vision encoder component.	None
qformer	Optional[RBLNModelConfig]	Configuration for the RBLN-optimized BLIP-2 Q-Former model.	None
language_model	Optional[RBLNModelConfig]	Configuration for the language model component.	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.

Functions