# AltCLIP ## 개요[[overview]] AltCLIP 모델은 Zhongzhi Chen, Guang Liu, Bo-Wen Zhang, Fulong Ye, Qinghong Yang, Ledell Wu의 [AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities](https://huggingface.co/papers/2211.06679) 논문에서 제안되었습니다. AltCLIP(CLIP의 언어 인코더를 변경하여 언어 기능 확장)은 다양한 이미지-텍스트 및 텍스트-텍스트 쌍으로 훈련된 신경망입니다. CLIP의 텍스트 인코더를 사전 훈련된 다국어 텍스트 인코더 XLM-R로 교체하여, 거의 모든 작업에서 CLIP과 유사한 성능을 얻을 수 있었으며, 원래 CLIP의 다국어 이해와 같은 기능도 확장되었습니다. 논문의 초록은 다음과 같습니다: *본 연구에서는 강력한 이중 언어 멀티모달 표현 모델을 훈련하는 개념적으로 간단하고 효과적인 방법을 제시합니다. OpenAI에서 출시한 사전 훈련된 멀티모달 표현 모델 CLIP에서 시작하여, 그 텍스트 인코더를 사전 훈련된 다국어 텍스트 인코더 XLM-R로 교체하고, 교사 학습과 대조 학습으로 구성된 2단계 훈련 스키마를 통해 언어와 이미지 표현을 정렬했습니다. 우리는 광범위한 작업 평가를 통해 우리의 방법을 검증했습니다. ImageNet-CN, Flicker30k-CN, COCO-CN을 포함한 여러 작업에서 새로운 최고 성능을 달성했으며, 거의 모든 작업에서 CLIP과 유사한 성능을 얻었습니다. 이는 CLIP의 텍스트 인코더를 단순히 변경하여 다국어 이해와 같은 확장 기능을 얻을 수 있음을 시사합니다.* 이 모델은 [jongjyh](https://huggingface.co/jongjyh)에 의해 기여되었습니다. ## 사용 팁과 예제[[usage-tips-and-example]] AltCLIP의 사용법은 CLIP과 매우 유사하며, 차이점은 텍스트 인코더에 있습니다. 일반적인 어텐션 대신 양방향 어텐션을 사용하며, XLM-R의 [CLS] 토큰을 사용하여 텍스트 임베딩을 나타냅니다. AltCLIP은 멀티모달 비전 및 언어 모델입니다. 이미지와 텍스트 간의 유사성 계산 및 제로샷 이미지 분류에 사용할 수 있습니다. AltCLIP은 ViT와 같은 트랜스포머를 사용하여 시각적 특징을 얻고, 양방향 언어 모델을 사용하여 텍스트 특징을 얻습니다. 이후 텍스트와 시각적 특징 모두 동일한 차원의 잠재 공간으로 투사됩니다. 투사된 이미지와 텍스트 특징 간의 내적을 유사도 점수로 사용합니다. 이미지를 트랜스포머 인코더에 입력하기 위해, 각 이미지를 일정한 크기의 겹치지 않는 패치 시퀀스로 분할한 뒤, 이를 선형 임베딩합니다. 전체 이미지를 나타내기 위해 [CLS] 토큰이 추가됩니다. 저자들은 절대 위치 임베딩도 추가하여 결과 벡터 시퀀스를 표준 트랜스포머 인코더에 입력합니다. [CLIPImageProcessor](/docs/transformers/v5.8.0/ko/model_doc/clip#transformers.CLIPImageProcessor)는 모델을 위해 이미지를 크기 조정하고 정규화하는 데 사용할 수 있습니다. [AltCLIPProcessor](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPProcessor)는 [CLIPImageProcessor](/docs/transformers/v5.8.0/ko/model_doc/clip#transformers.CLIPImageProcessor)와 `XLMRobertaTokenizer`를 하나의 인스턴스로 묶어 텍스트를 인코딩하고 이미지를 준비합니다. 다음 예제는 [AltCLIPProcessor](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPProcessor)와 [AltCLIPModel](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPModel)을 사용하여 이미지와 텍스트 간의 유사성 점수를 얻는 방법을 보여줍니다. ```python >>> from PIL import Image >>> import requests >>> from transformers import AltCLIPModel, AltCLIPProcessor >>> model = AltCLIPModel.from_pretrained("BAAI/AltCLIP") >>> processor = AltCLIPProcessor.from_pretrained("BAAI/AltCLIP") >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> image = Image.open(requests.get(url, stream=True).raw) >>> inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True) >>> outputs = model(**inputs) >>> logits_per_image = outputs.logits_per_image # 이미지-텍스트 유사도 점수 >>> probs = logits_per_image.softmax(dim=1) # 라벨 마다 확률을 얻기 위해 softmax 적용 ``` 이 모델은 `CLIPModel`을 기반으로 하므로, 원래 CLIP처럼 사용할 수 있습니다. ## AltCLIPConfig[[transformers.AltCLIPConfig]] #### transformers.AltCLIPConfig[[transformers.AltCLIPConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/configuration_altclip.py#L127) This is the configuration class to store the configuration of a AltCLIPModel. It is used to instantiate a Altclip model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the [BAAI/AltCLIP](https://huggingface.co/BAAI/AltCLIP) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/ko/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/ko/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import AltCLIPConfig, AltCLIPModel >>> # Initializing a AltCLIPConfig with BAAI/AltCLIP style configuration >>> configuration = AltCLIPConfig() >>> # Initializing a AltCLIPModel (with random weights) from the BAAI/AltCLIP style configuration >>> model = AltCLIPModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a AltCLIPConfig from a AltCLIPTextConfig and a AltCLIPVisionConfig >>> # Initializing a AltCLIPText and AltCLIPVision configuration >>> config_text = AltCLIPTextConfig() >>> config_vision = AltCLIPVisionConfig() >>> config = AltCLIPConfig(text_config=config_text, vision_config=config_vision) ``` **Parameters:** text_config (`Union[dict, ~models.altclip.configuration_altclip.AltCLIPTextConfig]`, *optional*) : The config object or dictionary of the text backbone. vision_config (`Union[dict, ~models.altclip.configuration_altclip.AltCLIPVisionConfig]`, *optional*) : The config object or dictionary of the vision backbone. projection_dim (`int`, *optional*, defaults to `768`) : Dimensionality of text and vision projection layers. logit_scale_init_value (`Union[float, int]`, *optional*, defaults to `2.6592`) : The initial value of the *logit_scale* parameter. initializer_factor (`float`, *optional*, defaults to `1.0`) : A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). ## AltCLIPTextConfig[[transformers.AltCLIPTextConfig]] #### transformers.AltCLIPTextConfig[[transformers.AltCLIPTextConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/configuration_altclip.py#L30) This is the configuration class to store the configuration of a AltCLIPModel. It is used to instantiate a Altclip model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the [BAAI/AltCLIP](https://huggingface.co/BAAI/AltCLIP) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/ko/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/ko/main_classes/configuration#transformers.PreTrainedConfig) for more information. Examples: ```python >>> from transformers import AltCLIPTextModel, AltCLIPTextConfig >>> # Initializing a AltCLIPTextConfig with BAAI/AltCLIP style configuration >>> configuration = AltCLIPTextConfig() >>> # Initializing a AltCLIPTextModel (with random weights) from the BAAI/AltCLIP style configuration >>> model = AltCLIPTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** vocab_size (`int`, *optional*, defaults to `250002`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`. hidden_size (`int`, *optional*, defaults to `1024`) : Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to `4096`) : Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to `24`) : Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to `16`) : Number of attention heads for each attention layer in the Transformer decoder. max_position_embeddings (`int`, *optional*, defaults to `514`) : The maximum sequence length that this model might ever be used with. hidden_act (`str`, *optional*, defaults to `gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc. layer_norm_eps (`float`, *optional*, defaults to `1e-05`) : The epsilon used by the layer normalization layers. initializer_range (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices. initializer_factor (`float`, *optional*, defaults to `0.02`) : A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). pad_token_id (`int`, *optional*, defaults to `1`) : Token id used for padding in the vocabulary. bos_token_id (`int`, *optional*, defaults to `0`) : Token id used for beginning-of-stream in the vocabulary. eos_token_id (`int`, *optional*, defaults to `2`) : Token id used for end-of-stream in the vocabulary. hidden_dropout_prob (`Union[int, float]`, *optional*, defaults to `0.1`) : The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`Union[int, float]`, *optional*, defaults to `0`) : The dropout ratio for the attention probabilities. type_vocab_size (`int`, *optional*, defaults to `1`) : The vocabulary size of the `token_type_ids`. project_dim (`int`, *optional*, defaults to 768) : The dimensions of the teacher model before the mapping layer. ## AltCLIPVisionConfig[[transformers.AltCLIPVisionConfig]] #### transformers.AltCLIPVisionConfig[[transformers.AltCLIPVisionConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/configuration_altclip.py#L82) This is the configuration class to store the configuration of a AltCLIPModel. It is used to instantiate a Altclip model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the [BAAI/AltCLIP](https://huggingface.co/BAAI/AltCLIP) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/ko/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/ko/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> from transformers import AltCLIPVisionConfig, AltCLIPVisionModel >>> # Initializing a AltCLIPVisionConfig with BAAI/AltCLIP style configuration >>> configuration = AltCLIPVisionConfig() >>> # Initializing a AltCLIPVisionModel (with random weights) from the BAAI/AltCLIP style configuration >>> model = AltCLIPVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** hidden_size (`int`, *optional*, defaults to `768`) : Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to `3072`) : Dimension of the MLP representations. projection_dim (`int`, *optional*, defaults to `512`) : Dimensionality of text and vision projection layers. num_hidden_layers (`int`, *optional*, defaults to `12`) : Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to `12`) : Number of attention heads for each attention layer in the Transformer decoder. num_channels (`int`, *optional*, defaults to `3`) : The number of input channels. image_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `224`) : The size (resolution) of each image. patch_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `32`) : The size (resolution) of each patch. hidden_act (`str`, *optional*, defaults to `quick_gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc. layer_norm_eps (`float`, *optional*, defaults to `1e-05`) : The epsilon used by the layer normalization layers. attention_dropout (`Union[int, float]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices. initializer_factor (`float`, *optional*, defaults to `1.0`) : A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). ## AltCLIPProcessor[[transformers.AltCLIPProcessor]] #### transformers.AltCLIPProcessor[[transformers.AltCLIPProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/processing_altclip.py#L23) Constructs a AltCLIPProcessor which wraps a image processor and a tokenizer into a single processor. [AltCLIPProcessor](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPProcessor) offers all the functionalities of [CLIPImageProcessor](/docs/transformers/v5.8.0/ko/model_doc/clip#transformers.CLIPImageProcessor) and `tokenizer_class`. See the [~CLIPImageProcessor](/docs/transformers/v5.8.0/ko/model_doc/clip#transformers.CLIPImageProcessor) and `~tokenizer_class` for more information. **Parameters:** image_processor (`CLIPImageProcessor`) : The image processor is a required input. tokenizer (`tokenizer_class`) : The tokenizer is a required input. ## AltCLIPModel[[transformers.AltCLIPModel]] #### transformers.AltCLIPModel[[transformers.AltCLIPModel]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/modeling_altclip.py#L943) The bare Altclip Model outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/ko/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. forwardtransformers.AltCLIPModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/modeling_altclip.py#L1037[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "token_type_ids", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "return_loss", "val": ": bool | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool = False"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/ko/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **pixel_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [CLIPImageProcessor](/docs/transformers/v5.8.0/ko/model_doc/clip#transformers.CLIPImageProcessor). See `CLIPImageProcessor.__call__()` for details ([AltCLIPProcessor](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPProcessor) uses [CLIPImageProcessor](/docs/transformers/v5.8.0/ko/model_doc/clip#transformers.CLIPImageProcessor) for processing images). - **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **token_type_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **return_loss** (`bool`, *optional*) -- Whether or not to return the contrastive loss. - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings.0`AltCLIPOutput` or `tuple(torch.FloatTensor)`A `AltCLIPOutput` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([AltCLIPConfig](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPConfig)) and inputs. The [AltCLIPModel](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPModel) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `return_loss` is `True`) -- Contrastive loss for image-text similarity. - **logits_per_image** (`torch.FloatTensor` of shape `(image_batch_size, text_batch_size)`) -- The scaled dot product scores between `image_embeds` and `text_embeds`. This represents the image-text similarity scores. - **logits_per_text** (`torch.FloatTensor` of shape `(text_batch_size, image_batch_size)`) -- The scaled dot product scores between `text_embeds` and `image_embeds`. This represents the text-image similarity scores. - **text_embeds** (`torch.FloatTensor` of shape `(batch_size, output_dim`) -- The text embeddings obtained by applying the projection layer to the pooled output of [AltCLIPTextModel](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPTextModel). - **image_embeds** (`torch.FloatTensor` of shape `(batch_size, output_dim`) -- The image embeddings obtained by applying the projection layer to the pooled output of [AltCLIPVisionModel](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPVisionModel). - **text_model_output** (`~modeling_outputs.BaseModelOutputWithPooling`, defaults to `None`) -- The output of the [AltCLIPTextModel](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPTextModel). - **vision_model_output** (`~modeling_outputs.BaseModelOutputWithPooling`, defaults to `None`) -- The output of the [AltCLIPVisionModel](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPVisionModel). Examples: ```python >>> import torch >>> from transformers import AutoProcessor, AltCLIPModel >>> from transformers.image_utils import load_image >>> model = AltCLIPModel.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16") >>> processor = AutoProcessor.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16") >>> url = "https://clip-cn-beijing.oss-cn-beijing.aliyuncs.com/pokemon.jpeg" >>> image = load_image(url) >>> inputs = processor(text=["杰尼龟", "妙蛙种子", "小火龙", "皮卡丘"], images=image, return_tensors="pt", padding=True) >>> with torch.inference_mode(): ... outputs = model(**inputs) >>> logits_per_image = outputs.logits_per_image # this is the image-text similarity score >>> probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities ``` **Parameters:** config ([AltCLIPConfig](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.8.0/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``AltCLIPOutput` or `tuple(torch.FloatTensor)`` A `AltCLIPOutput` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([AltCLIPConfig](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPConfig)) and inputs. #### get_text_features[[transformers.AltCLIPModel.get_text_features]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/modeling_altclip.py#L964) - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Examples: ```python >>> import torch >>> from transformers import AutoProcessor, AltCLIPModel >>> model = AltCLIPModel.from_pretrained("BAAI/AltCLIP") >>> processor = AutoProcessor.from_pretrained("BAAI/AltCLIP") >>> inputs = processor(text=["a photo of a cat", "a photo of a dog"], padding=True, return_tensors="pt") >>> with torch.inference_mode(): ... text_features = model.get_text_features(**inputs) ``` **Parameters:** input_ids (`torch.Tensor` of shape `(batch_size, sequence_length)`) : Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/ko/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) token_type_ids (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) position_ids (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/v5.8.0/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/v5.8.0/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([AltCLIPConfig](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPConfig)) and inputs. #### get_image_features[[transformers.AltCLIPModel.get_image_features]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/modeling_altclip.py#L1000) - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Examples: ```python >>> import torch >>> from transformers import AutoProcessor, AltCLIPModel >>> from transformers.image_utils import load_image >>> model = AltCLIPModel.from_pretrained("BAAI/AltCLIP") >>> processor = AutoProcessor.from_pretrained("BAAI/AltCLIP") >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> image = load_image(url) >>> inputs = processor(images=image, return_tensors="pt") >>> with torch.inference_mode(): ... image_features = model.get_image_features(**inputs) ``` **Parameters:** pixel_values (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`) : The tensors corresponding to the input images. Pixel values can be obtained using [CLIPImageProcessor](/docs/transformers/v5.8.0/ko/model_doc/clip#transformers.CLIPImageProcessor). See `CLIPImageProcessor.__call__()` for details ([AltCLIPProcessor](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPProcessor) uses [CLIPImageProcessor](/docs/transformers/v5.8.0/ko/model_doc/clip#transformers.CLIPImageProcessor) for processing images). interpolate_pos_encoding (`bool`, *optional*, defaults to `False`) : Whether to interpolate the pre-trained position encodings. **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/v5.8.0/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/v5.8.0/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([AltCLIPConfig](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPConfig)) and inputs. ## AltCLIPTextModel[[transformers.AltCLIPTextModel]] #### transformers.AltCLIPTextModel[[transformers.AltCLIPTextModel]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/modeling_altclip.py#L850) forwardtransformers.AltCLIPTextModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/modeling_altclip.py#L863[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "token_type_ids", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.Tensor | None = None"}, {"name": "inputs_embeds", "val": ": torch.Tensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **input_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/ko/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) - **attention_mask** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) - **token_type_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) - **position_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) -- Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) - **inputs_embeds** (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix.0`BaseModelOutputWithPoolingAndProjection` or `tuple(torch.FloatTensor)`A `BaseModelOutputWithPoolingAndProjection` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([AltCLIPConfig](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPConfig)) and inputs. The [AltCLIPTextModel](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPTextModel) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. - **projection_state** (`tuple(torch.FloatTensor)`, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` of shape `(batch_size,config.project_dim)`. Text embeddings before the projection layer, used to mimic the last hidden state of the teacher encoder. Examples: ```python >>> from transformers import AutoProcessor, AltCLIPTextModel >>> model = AltCLIPTextModel.from_pretrained("BAAI/AltCLIP") >>> processor = AutoProcessor.from_pretrained("BAAI/AltCLIP") >>> texts = ["it's a cat", "it's a dog"] >>> inputs = processor(text=texts, padding=True, return_tensors="pt") >>> outputs = model(**inputs) >>> last_hidden_state = outputs.last_hidden_state >>> pooled_output = outputs.pooler_output # pooled CLS states ``` **Parameters:** input_ids (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Indices of input sequence tokens in the vocabulary. Padding will be ignored by default. Indices can be obtained using [AutoTokenizer](/docs/transformers/v5.8.0/ko/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.8.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.8.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#input-ids) attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) token_type_ids (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`: - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token. [What are token type IDs?](../glossary#token-type-ids) position_ids (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) inputs_embeds (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) : Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. **Returns:** ``BaseModelOutputWithPoolingAndProjection` or `tuple(torch.FloatTensor)`` A `BaseModelOutputWithPoolingAndProjection` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([AltCLIPConfig](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPConfig)) and inputs. ## AltCLIPVisionModel[[transformers.AltCLIPVisionModel]] #### transformers.AltCLIPVisionModel[[transformers.AltCLIPVisionModel]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/modeling_altclip.py#L697) The vision model from ALTCLIP without any head or projection on top. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/ko/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. forwardtransformers.AltCLIPVisionModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/altclip/modeling_altclip.py#L713[{"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool | None = False"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **pixel_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [CLIPImageProcessor](/docs/transformers/v5.8.0/ko/model_doc/clip#transformers.CLIPImageProcessor). See `CLIPImageProcessor.__call__()` for details ([AltCLIPProcessor](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPProcessor) uses [CLIPImageProcessor](/docs/transformers/v5.8.0/ko/model_doc/clip#transformers.CLIPImageProcessor) for processing images). - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings.0[BaseModelOutputWithPooling](/docs/transformers/v5.8.0/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`A [BaseModelOutputWithPooling](/docs/transformers/v5.8.0/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([AltCLIPConfig](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPConfig)) and inputs. The [AltCLIPVisionModel](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPVisionModel) forward method, overrides the `__call__` special method. Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them. - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the model. - **pooler_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) -- Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. - **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states of the model at the output of each layer plus the optional initial embedding outputs. - **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`. Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads. Examples: ```python >>> import httpx >>> from io import BytesIO >>> from PIL import Image >>> from transformers import AutoProcessor, AltCLIPVisionModel >>> model = AltCLIPVisionModel.from_pretrained("BAAI/AltCLIP") >>> processor = AutoProcessor.from_pretrained("BAAI/AltCLIP") >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())) >>> inputs = processor(images=image, return_tensors="pt") >>> outputs = model(**inputs) >>> last_hidden_state = outputs.last_hidden_state >>> pooled_output = outputs.pooler_output # pooled CLS states ``` **Parameters:** config ([AltCLIPVisionConfig](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPVisionConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.8.0/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[BaseModelOutputWithPooling](/docs/transformers/v5.8.0/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [BaseModelOutputWithPooling](/docs/transformers/v5.8.0/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration ([AltCLIPConfig](/docs/transformers/v5.8.0/ko/model_doc/altclip#transformers.AltCLIPConfig)) and inputs.