KOSMOS-2
Overview
The KOSMOS-2 model was proposed in Kosmos-2: Grounding Multimodal Large Language Models to the World by Zhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao, Shaohan Huang, Shuming Ma, Furu Wei.
KOSMOS-2 is a Transformer-based causal language model and is trained using the next-word prediction task on a web-scale
dataset of grounded image-text pairs GRIT. The spatial coordinates of
the bounding boxes in the dataset are converted to a sequence of location tokens, which are appended to their respective
entity text spans (for example, a snowman followed by <patch_index_0044><patch_index_0863>). The data format is
similar to “hyperlinks” that connect the object regions in an image to their text span in the corresponding caption.
The abstract from the paper is the following:
We introduce Kosmos-2, a Multimodal Large Language Model (MLLM), enabling new capabilities of perceiving object descriptions (e.g., bounding boxes) and grounding text to the visual world. Specifically, we represent refer expressions as links in Markdown, i.e., “[text span](bounding boxes)”, where object descriptions are sequences of location tokens. Together with multimodal corpora, we construct large-scale data of grounded image-text pairs (called GrIT) to train the model. In addition to the existing capabilities of MLLMs (e.g., perceiving general modalities, following instructions, and performing in-context learning), Kosmos-2 integrates the grounding capability into downstream applications. We evaluate Kosmos-2 on a wide range of tasks, including (i) multimodal grounding, such as referring expression comprehension, and phrase grounding, (ii) multimodal referring, such as referring expression generation, (iii) perception-language tasks, and (iv) language understanding and generation. This work lays out the foundation for the development of Embodiment AI and sheds light on the big convergence of language, multimodal perception, action, and world modeling, which is a key step toward artificial general intelligence. Code and pretrained models are available at https://aka.ms/kosmos-2.
Overview of tasks that KOSMOS-2 can handle. Taken from the original paper. Example
>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, Kosmos2ForConditionalGeneration
>>> model = Kosmos2ForConditionalGeneration.from_pretrained("microsoft/kosmos-2-patch14-224")
>>> processor = AutoProcessor.from_pretrained("microsoft/kosmos-2-patch14-224")
>>> url = "https://huggingface.co/microsoft/kosmos-2-patch14-224/resolve/main/snowman.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> prompt = "<grounding> An image of"
>>> inputs = processor(text=prompt, images=image, return_tensors="pt")
>>> generated_ids = model.generate(
... pixel_values=inputs["pixel_values"],
... input_ids=inputs["input_ids"],
... attention_mask=inputs["attention_mask"],
... image_embeds=None,
... image_embeds_position_mask=inputs["image_embeds_position_mask"],
... use_cache=True,
... max_new_tokens=64,
... )
>>> generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
>>> processed_text = processor.post_process_generation(generated_text, cleanup_and_extract=False)
>>> processed_text
'<grounding> An image of<phrase> a snowman</phrase><object><patch_index_0044><patch_index_0863></object> warming himself by<phrase> a fire</phrase><object><patch_index_0005><patch_index_0911></object>.'
>>> caption, entities = processor.post_process_generation(generated_text)
>>> caption
'An image of a snowman warming himself by a fire.'
>>> entities
[('a snowman', (12, 21), [(0.390625, 0.046875, 0.984375, 0.828125)]), ('a fire', (41, 47), [(0.171875, 0.015625, 0.484375, 0.890625)])]This model was contributed by Yih-Dar SHIEH. The original code can be found here.
Kosmos2Config
class transformers.Kosmos2Config
< source >( text_config = None vision_config = None latent_query_num = 64 **kwargs )
Parameters
- text_config (
dict, optional) — Dictionary of configuration options used to initializeKosmos2TextConfig. - vision_config (
dict, optional) — Dictionary of configuration options used to initializeKosmos2VisionConfig. - latent_query_num (
int, optional, defaults to 64) — The number of latent query tokens that represent the image features used in the text decoder component. - kwargs (optional) — Dictionary of keyword arguments.
This is the configuration class to store the configuration of a Kosmos2Model. It is used to instantiate a KOSMOS-2 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 KOSMOS-2 microsoft/kosmos-2-patch14-224 architecture.
Example:
>>> from transformers import Kosmos2Config, Kosmos2Model
>>> # Initializing a Kosmos-2 kosmos-2-patch14-224 style configuration
>>> configuration = Kosmos2Config()
>>> # Initializing a model (with random weights) from the kosmos-2-patch14-224 style configuration
>>> model = Kosmos2Model(configuration)
>>> # Accessing the model configuration
>>> configuration = model.configKosmos2ImageProcessor
Kosmos2Processor
class transformers.Kosmos2Processor
< source >( image_processor tokenizer num_patch_index_tokens = 1024 )
Parameters
- image_processor (
CLIPImageProcessor) — An instance of CLIPImageProcessor. The image processor is a required input. - tokenizer (
XLMRobertaTokenizerFast) — An instance of [‘XLMRobertaTokenizerFast`]. The tokenizer is a required input. - num_patch_index_tokens (
int, optional, defaults to 1024) — The number of tokens that represent patch indices.
Constructs an KOSMOS-2 processor which wraps a KOSMOS-2 image processor and a KOSMOS-2 tokenizer into a single processor.
Kosmos2Processor offers all the functionalities of CLIPImageProcessor and some functionalities of
XLMRobertaTokenizerFast. See the docstring of call() and decode()
for more information.
__call__
< source >( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[ForwardRef('PIL.Image.Image')], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')]] = None text: typing.Union[str, typing.List[str]] = None bboxes: typing.Union[typing.List[typing.Tuple[int, int]], typing.List[typing.Tuple[float, float, float, float]], typing.List[typing.List[typing.Tuple[int, int]]], typing.List[typing.List[typing.Tuple[float, float, float]]]] = None num_image_tokens: typing.Optional[int] = 64 first_image_token_id: typing.Optional[int] = None add_special_tokens: bool = True add_eos_token: bool = False padding: typing.Union[bool, str, transformers.utils.generic.PaddingStrategy] = False truncation: typing.Union[bool, str, transformers.tokenization_utils_base.TruncationStrategy] = None max_length: typing.Optional[int] = None pad_to_multiple_of: typing.Optional[int] = None return_attention_mask: typing.Optional[bool] = None return_length: bool = False verbose: bool = True return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None **kwargs )
Parameters
- bboxes (
Union[List[Tuple[int]], List[Tuple[float]], List[List[Tuple[int]]], List[List[Tuple[float]]]], optional) — The bounding bboxes associated totexts. - num_image_tokens (
int, defaults to 64) — The number of (consecutive) places that are used to mark the placeholders to store image information. This should be the same aslatent_query_numin the instance ofKosmos2Configyou are using. - first_image_token_id (
int, optional) — The token id that will be used for the first place of the subsequence that is reserved to store image information. If unset, will default toself.tokenizer.unk_token_id + 1. - add_eos_token (
bool, defaults toFalse) — Whether or not to includeEOStoken id in the encoding whenadd_special_tokens=True.
This method uses CLIPImageProcessor.call() method to prepare image(s) for the model, and XLMRobertaTokenizerFast.call() to prepare text for the model.
Please refer to the docstring of the above two methods for more information.
The rest of this documentation shows the arguments specific to Kosmos2Processor.
Kosmos2Model
class transformers.Kosmos2Model
< source >( config: Kosmos2Config )
Parameters
- config (Kosmos2Config) — 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() method to load the model weights.
KOSMOS-2 Model for generating text and image features. The model consists of a vision encoder and a language model.
This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( pixel_values: typing.Optional[torch.Tensor] = None input_ids: typing.Optional[torch.Tensor] = None image_embeds_position_mask: typing.Optional[torch.Tensor] = None attention_mask: typing.Optional[torch.Tensor] = None head_mask: typing.Optional[torch.Tensor] = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None image_embeds: typing.Optional[torch.Tensor] = None inputs_embeds: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.Tensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.models.kosmos2.modeling_kosmos2.Kosmos2ModelOutput or tuple(torch.FloatTensor)
Parameters
- pixel_values (
torch.FloatTensorof shape(batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See CLIPImageProcessor.call() for details. - input_ids (
torch.LongTensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- image_embeds_position_mask (
torch.Tensorof shape(batch_size, sequence_length), optional) — Mask to indicate the location in a sequence to insert the image features . Mask values selected in[0, 1]:- 1 for places where to put the image features,
- 0 for places that are not for image features (i.e. for text tokens).
- attention_mask (
torch.Tensorof 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.
- head_mask (
torch.FloatTensorof shape(num_heads,)or(num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- past_key_values (
tuple(tuple(torch.FloatTensor))of lengthconfig.n_layerswith each tuple having 4 tensors of shape(batch_size, num_heads, sequence_length - 1, embed_size_per_head)) — Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.If
past_key_valuesare used, the user can optionally input only the lastdecoder_input_ids(those that don’t have their past key value states given to this model) of shape(batch_size, 1)instead of alldecoder_input_idsof shape(batch_size, sequence_length). image_embeds — (torch.FloatTensorof shape(batch_size, latent_query_num, hidden_size), optional): Sequence of hidden-states at the output ofKosmos2ImageToTextProjection. - inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - position_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]. - use_cache (
bool, optional) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). - output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.models.kosmos2.modeling_kosmos2.Kosmos2ModelOutput or tuple(torch.FloatTensor)
A transformers.models.kosmos2.modeling_kosmos2.Kosmos2ModelOutput 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 (<class 'transformers.models.kosmos2.configuration_kosmos2.Kosmos2Config'>) and inputs.
-
last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model. -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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.
-
image_embeds (
torch.FloatTensorof shape(batch_size, latent_query_num, hidden_size), optional) — Sequence of hidden-states at the output ofKosmos2ImageToTextProjection. -
projection_attentions (
tuple(torch.FloatTensor), optional) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights given by
Kosmos2ImageToTextProjection, after the attention softmax, used to compute the weighted average in the self-attention heads. -
vision_model_output(
BaseModelOutputWithPooling, optional) — The output of theKosmos2VisionModel. -
past_key_values (
tuple(tuple(torch.FloatTensor)), optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — Tuple oftuple(torch.FloatTensor)of lengthconfig.n_layers, with each tuple having 2 tensors of shape(batch_size, num_heads, sequence_length, embed_size_per_head)) and optionally ifconfig.is_encoder_decoder=True2 additional tensors of shape(batch_size, num_heads, encoder_sequence_length, embed_size_per_head).Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if
config.is_encoder_decoder=Truein the cross-attention blocks) that can be used (seepast_key_valuesinput) to speed up sequential decoding.
The Kosmos2Model 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.
Examples:
>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, Kosmos2Model
>>> model = Kosmos2Model.from_pretrained("microsoft/kosmos-2-patch14-224")
>>> processor = AutoProcessor.from_pretrained("microsoft/kosmos-2-patch14-224")
>>> url = "https://huggingface.co/microsoft/kosmos-2-patch14-224/resolve/main/snowman.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> text = (
... "<grounding> An image of<phrase> a snowman</phrase><object><patch_index_0044><patch_index_0863>"
... "</object> warming himself by<phrase> a fire</phrase><object><patch_index_0005><patch_index_0911>"
... "</object>"
... )
>>> inputs = processor(text=text, images=image, return_tensors="pt", add_eos_token=True)
>>> last_hidden_state = model(
... pixel_values=inputs["pixel_values"],
... input_ids=inputs["input_ids"],
... attention_mask=inputs["attention_mask"],
... image_embeds_position_mask=inputs["image_embeds_position_mask"],
... ).last_hidden_state
>>> list(last_hidden_state.shape)
[1, 91, 2048]Kosmos2ForConditionalGeneration
class transformers.Kosmos2ForConditionalGeneration
< source >( config: Kosmos2Config )
Parameters
- config (Kosmos2Config) — 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() method to load the model weights.
KOSMOS-2 Model for generating text and bounding boxes given an image. The model consists of a vision encoder and a language model.
This model inherits from 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 subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( pixel_values: typing.Optional[torch.Tensor] = None input_ids: typing.Optional[torch.Tensor] = None image_embeds_position_mask: typing.Optional[torch.Tensor] = None attention_mask: typing.Optional[torch.Tensor] = None head_mask: typing.Optional[torch.Tensor] = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None image_embeds: typing.Optional[torch.Tensor] = None inputs_embeds: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.Tensor] = None labels: typing.Optional[torch.LongTensor] = None use_cache: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.models.kosmos2.modeling_kosmos2.Kosmos2ForConditionalGenerationModelOutput or tuple(torch.FloatTensor)
Parameters
- pixel_values (
torch.FloatTensorof shape(batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See CLIPImageProcessor.call() for details. - input_ids (
torch.LongTensorof shape(batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- image_embeds_position_mask (
torch.Tensorof shape(batch_size, sequence_length), optional) — Mask to indicate the location in a sequence to insert the image features . Mask values selected in[0, 1]:- 1 for places where to put the image features,
- 0 for places that are not for image features (i.e. for text tokens).
- attention_mask (
torch.Tensorof 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.
- head_mask (
torch.FloatTensorof shape(num_heads,)or(num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in[0, 1]:- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- past_key_values (
tuple(tuple(torch.FloatTensor))of lengthconfig.n_layerswith each tuple having 4 tensors of shape(batch_size, num_heads, sequence_length - 1, embed_size_per_head)) — Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.If
past_key_valuesare used, the user can optionally input only the lastdecoder_input_ids(those that don’t have their past key value states given to this model) of shape(batch_size, 1)instead of alldecoder_input_idsof shape(batch_size, sequence_length). image_embeds — (torch.FloatTensorof shape(batch_size, latent_query_num, hidden_size), optional): Sequence of hidden-states at the output ofKosmos2ImageToTextProjection. - inputs_embeds (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passinginput_idsyou can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_idsindices into associated vectors than the model’s internal embedding lookup matrix. - position_ids (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.max_position_embeddings - 1]. - use_cache (
bool, optional) — If set toTrue,past_key_valueskey value states are returned and can be used to speed up decoding (seepast_key_values). - output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensorof shape(batch_size, sequence_length), optional) — Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in[-100, 0, ..., config.vocab_size](seeinput_idsdocstring) Tokens with indices set to-100are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., config.vocab_size]
Returns
transformers.models.kosmos2.modeling_kosmos2.Kosmos2ForConditionalGenerationModelOutput or tuple(torch.FloatTensor)
A transformers.models.kosmos2.modeling_kosmos2.Kosmos2ForConditionalGenerationModelOutput 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 (<class 'transformers.models.kosmos2.configuration_kosmos2.Kosmos2Config'>) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Language modeling loss (for next-token prediction). -
logits (
torch.FloatTensorof shape(batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.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 whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.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.
-
image_embeds (
torch.FloatTensorof shape(batch_size, latent_query_num, hidden_size), optional) — Sequence of hidden-states at the output ofKosmos2ImageToTextProjection. -
projection_attentions (
tuple(torch.FloatTensor), optional) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights given by
Kosmos2ImageToTextProjection, after the attention softmax, used to compute the weighted average in the self-attention heads. -
vision_model_output(
BaseModelOutputWithPooling, optional) — The output of theKosmos2VisionModel. -
past_key_values (
tuple(tuple(torch.FloatTensor)), optional, returned whenuse_cache=Trueis passed or whenconfig.use_cache=True) — Tuple oftuple(torch.FloatTensor)of lengthconfig.n_layers, with each tuple having 2 tensors of shape(batch_size, num_heads, sequence_length, embed_size_per_head)) and optionally ifconfig.is_encoder_decoder=True2 additional tensors of shape(batch_size, num_heads, encoder_sequence_length, embed_size_per_head).Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if
config.is_encoder_decoder=Truein the cross-attention blocks) that can be used (seepast_key_valuesinput) to speed up sequential decoding.
The Kosmos2ForConditionalGeneration 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.
Examples:
>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, Kosmos2ForConditionalGeneration
>>> model = Kosmos2ForConditionalGeneration.from_pretrained("microsoft/kosmos-2-patch14-224")
>>> processor = AutoProcessor.from_pretrained("microsoft/kosmos-2-patch14-224")
>>> url = "https://huggingface.co/microsoft/kosmos-2-patch14-224/resolve/main/snowman.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> prompt = "<grounding> An image of"
>>> inputs = processor(text=prompt, images=image, return_tensors="pt")
>>> generated_ids = model.generate(
... pixel_values=inputs["pixel_values"],
... input_ids=inputs["input_ids"],
... attention_mask=inputs["attention_mask"],
... image_embeds=None,
... image_embeds_position_mask=inputs["image_embeds_position_mask"],
... use_cache=True,
... max_new_tokens=64,
... )
>>> generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
>>> processed_text = processor.post_process_generation(generated_text, cleanup_and_extract=False)
>>> processed_text
'<grounding> An image of<phrase> a snowman</phrase><object><patch_index_0044><patch_index_0863></object> warming himself by<phrase> a fire</phrase><object><patch_index_0005><patch_index_0911></object>.'
>>> caption, entities = processor.post_process_generation(generated_text)
>>> caption
'An image of a snowman warming himself by a fire.'
>>> entities
[('a snowman', (12, 21), [(0.390625, 0.046875, 0.984375, 0.828125)]), ('a fire', (41, 47), [(0.171875, 0.015625, 0.484375, 0.890625)])]