CLIP

CLIP (Contrastive Language-Image Pre-training)은 OpenAI에서 개발한 텍스트와 이미지를 연결하는 멀티모달 모델입니다. 시각적 정보와 텍스트 정보를 모두 이해할 수 있도록 인터넷에서 수집한 다양한 이미지-텍스트 쌍 데이터셋에서 훈련되었습니다. CLIP은 제로샷 분류를 수행할 수 있으며 강력한 이미지-텍스트 매칭 기능을 갖추고 있습니다. RBLN NPU는 Optimum RBLN을 사용하여 CLIP 모델 추론을 가속화할 수 있습니다.

주요 클래스

• RBLNCLIPTextModel: RBLN NPU에서 텍스트 인코딩을 위한 CLIP 텍스트 모델 구현
• RBLNCLIPTextModelConfig: CLIP 텍스트 모델의 설정 클래스
• RBLNCLIPTextModelWithProjection: 멀티모달 작업을 위한 프로젝션이 포함된 CLIP 텍스트 모델
• RBLNCLIPTextModelWithProjectionConfig: 프로젝션이 포함된 CLIP 텍스트 모델의 설정 클래스
• RBLNCLIPVisionModel: RBLN NPU에서 이미지 인코딩을 위한 CLIP 비전 모델 구현
• RBLNCLIPVisionModelConfig: CLIP 비전 모델의 설정 클래스
• RBLNCLIPVisionModelWithProjection: 멀티모달 작업을 위한 프로젝션이 포함된 CLIP 비전 모델
• RBLNCLIPVisionModelWithProjectionConfig: 프로젝션이 포함된 CLIP 비전 모델의 설정 클래스

API 참조

Classes

RBLNCLIPTextModel

Bases: RBLNModel

Functions

forward(input_ids, return_dict=None, **kwargs)

Parameters:

Name	Type	Description	Default
input_ids	LongTensor	Input IDs.	required
return_dict	bool	Whether or not to return a ModelOutput instead of a plain tuple.	None
**kwargs	Dict[str, Any]	Additional arguments.	{}

Returns:

Type	Description
Union[CLIPTextModelOutput, Tuple]	Union[CLIPTextModelOutput, Tuple]: The output of the model.

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

RBLNCLIPTextModelWithProjection

Bases: RBLNCLIPTextModel

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

forward(input_ids, return_dict=None, **kwargs)

Parameters:

Name	Type	Description	Default
input_ids	LongTensor	Input IDs.	required
return_dict	bool	Whether or not to return a ModelOutput instead of a plain tuple.	None
**kwargs	Dict[str, Any]	Additional arguments.	{}

Returns:

Type	Description
Union[CLIPTextModelOutput, Tuple]	Union[CLIPTextModelOutput, Tuple]: The output of the model.

RBLNCLIPVisionModel

Bases: RBLNModel

Functions

forward(pixel_values=None, return_dict=None, **kwargs)

Parameters:

Name	Type	Description	Default
pixel_values	Optional[FloatTensor]	Input pixel values.	None
return_dict	bool	Whether or not to return a ModelOutput instead of a plain tuple.	None
**kwargs	Dict[str, Any]	Additional arguments.	{}

Returns:

Type	Description
Union[CLIPVisionModelOutput, Tuple]	Union[CLIPVisionModelOutput, Tuple]: The output of the model.

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

RBLNCLIPVisionModelWithProjection

Bases: RBLNCLIPVisionModel

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

forward(pixel_values=None, return_dict=None, **kwargs)

Parameters:

Name	Type	Description	Default
pixel_values	Optional[FloatTensor]	Input pixel values.	None
return_dict	bool	Whether or not to return a ModelOutput instead of a plain tuple.	None
**kwargs	Dict[str, Any]	Additional arguments.	{}

Returns:

Type	Description
Union[CLIPVisionModelOutput, Tuple]	Union[CLIPVisionModelOutput, Tuple]: The output of the model.

Classes

RBLNCLIPTextModelConfig

Bases: RBLNModelConfig

Functions

__init__(batch_size=None, **kwargs)

Parameters:

Name	Type	Description	Default
batch_size	Optional[int]	The batch size for text processing. Defaults to 1.	None
**kwargs	Dict[str, Any]	Additional arguments passed to the parent RBLNModelConfig.	{}

Raises:

Type	Description
ValueError	If batch_size is not a positive integer.

RBLNCLIPTextModelWithProjectionConfig

Bases: RBLNCLIPTextModelConfig

Functions

__init__(batch_size=None, **kwargs)

Parameters:

Name	Type	Description	Default
batch_size	Optional[int]	The batch size for text processing. Defaults to 1.	None
**kwargs	Dict[str, Any]	Additional arguments passed to the parent RBLNModelConfig.	{}

Raises:

Type	Description
ValueError	If batch_size is not a positive integer.

RBLNCLIPVisionModelConfig

Bases: RBLNModelConfig

Functions

__init__(batch_size=None, image_size=None, **kwargs)

Parameters:

Name	Type	Description	Default
batch_size	Optional[int]	The batch size for image processing. Defaults to 1.	None
image_size	Optional[int]	The size of input images. Can be an integer for square images, a tuple/list (height, width), or a dictionary with 'height' and 'width' keys.	None
**kwargs	Dict[str, Any]	Additional arguments passed to the parent RBLNModelConfig.	{}

Raises:

Type	Description
ValueError	If batch_size is not a positive integer.

RBLNCLIPVisionModelWithProjectionConfig

Bases: RBLNCLIPVisionModelConfig

Functions

__init__(batch_size=None, image_size=None, **kwargs)

Parameters:

Name	Type	Description	Default
batch_size	Optional[int]	The batch size for image processing. Defaults to 1.	None
image_size	Optional[int]	The size of input images. Can be an integer for square images, a tuple/list (height, width), or a dictionary with 'height' and 'width' keys.	None
**kwargs	Dict[str, Any]	Additional arguments passed to the parent RBLNModelConfig.	{}

Raises:

Type	Description
ValueError	If batch_size is not a positive integer.