Transformers documentation

PaliGemma

Transformers

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v4.47.1).

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

PaliGemma

Overview

The PaliGemma model was proposed in PaliGemma – Google’s Cutting-Edge Open Vision Language Model by Google. It is a 3B vision-language model composed by a SigLIP vision encoder and a Gemma language decoder linked by a multimodal linear projection. It cuts an image into a fixed number of VIT tokens and prepends it to an optional prompt. One particularity is that the model uses full block attention on all the image tokens plus the input text tokens. It comes in 3 resolutions, 224x224, 448x448 and 896x896 with 3 base models, with 55 fine-tuned versions for different tasks, and 2 mix models.

PaliGemma architecture. Taken from the blog post.

This model was contributed by Molbap.

Usage tips

PaliGemma is not meant for conversational use, and it works best when fine-tuning to a specific use case. Some downstream tasks on which PaliGemma can be fine-tuned include image captioning, visual question answering (VQA), object detection, referring expression segmentation and document understanding.
One can use PaliGemmaProcessor to prepare images, text and optional labels for the model. When fine-tuning a PaliGemma model, the suffix argument can be passed to the processor which creates the labels for the model:

prompt = "What is on the flower?"
answer = "a bee"
inputs = processor(images=raw_image, text=prompt, suffix=answer, return_tensors="pt")

Usage Example

The model can accept a single or multiple images. According to the paper, the checkpoint PaliGemma can transfer to tasks which take multiple images as input. NLVR2 is one such task, which asks one question about two images, and requires looking at both to give the correct answer. Here’s an example code for single and multi image inference.

Single-image Inference

from transformers import AutoProcessor, PaliGemmaForConditionalGeneration

model_id = "google/paligemma-3b-mix-224"
model = PaliGemmaForConditionalGeneration.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id)

prompt = "What is on the flower?"
image_file = "https://huggingface.co./datasets/huggingface/documentation-images/resolve/main/bee.jpg?download=true"
raw_image = Image.open(requests.get(image_file, stream=True).raw)
inputs = processor(raw_image, prompt, return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=20)

print(processor.decode(output[0], skip_special_tokens=True)[inputs.input_ids.shape[1]: ])

Multi-image Inference

model_id = "google/paligemma-3b-ft-nlvr2-448"  # checkpoint tuned for multiple images
model = PaliGemmaForConditionalGeneration.from_pretrained(model_id)
processor = PaliGemmaProcessor.from_pretrained(model_id)

prompt = "answer en Which of the two pictures shows a snowman, first or second?"
stop_sign_image = Image.open(
    requests.get("https://www.ilankelman.org/stopsigns/australia.jpg", stream=True).raw
)
snow_image = Image.open(
    requests.get(
        "https://huggingface.co./microsoft/kosmos-2-patch14-224/resolve/main/snowman.jpg", stream=True
    ).raw
)

inputs = processor(images=[[snow_image, stop_sign_image]], text=prompt, return_tensors="pt")

output = model.generate(**inputs, max_new_tokens=20)
print(processor.decode(output[0], skip_special_tokens=True)[inputs.input_ids.shape[1]: ])

Resources

A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with PaliGemma. If you’re interested in submitting a resource to be included here, please feel free to open a Pull Request and we’ll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.

A blog post introducing all the features of PaliGemma can be found here.
Demo notebooks on how to fine-tune PaliGemma for VQA with the Trainer API along with inference can be found here.
Demo notebooks on how to fine-tune PaliGemma on a custom dataset (receipt image -> JSON) along with inference can be found here. 🌎

PaliGemmaConfig

class transformers.PaliGemmaConfig

< source >

( vision_config = None text_config = None ignore_index = -100 image_token_index = 256000 vocab_size = 257152 projection_dim = 2048 hidden_size = 2048 **kwargs )

Parameters

vision_config (PaliGemmaVisionConfig, optional) — Custom vision config or dict
text_config (Union[AutoConfig, dict], optional) — The config object of the text backbone. Can be any of LlamaConfig or MistralConfig.
ignore_index (int, optional, defaults to -100) — The ignore index for the loss function.
image_token_index (int, optional, defaults to 256000) — The image token index to encode the image prompt.
vocab_size (int, optional, defaults to 257152) — Vocabulary size of the PaliGemmamodel. Defines the number of different tokens that can be represented by the inputs_ids passed when calling ~PaliGemmaForConditionalGeneration
projection_dim (int, optional, defaults to 2048) — Dimension of the multimodal projection space.
hidden_size (int, optional, defaults to 2048) — Dimension of the hidden layer of the Language model.

This is the configuration class to store the configuration of a PaliGemmaForConditionalGeneration. It is used to instantiate an PaliGemmamodel according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the PaliGemma-2B.

e.g. paligemma-hf/paligemma-2b

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

Example:

>>> from transformers import PaliGemmaForConditionalGeneration, PaliGemmaConfig, SiglipVisionConfig, GemmaConfig

>>> # Initializing a Siglip-like vision config
>>> vision_config = SiglipVisionConfig()

>>> # Initializing a PaliGemma config
>>> text_config = GemmaConfig()

>>> # Initializing a PaliGemma paligemma-3b-224 style configuration
>>> configuration = PaliGemmaConfig(vision_config, text_config)

>>> # Initializing a model from the paligemma-3b-224 style configuration
>>> model = PaliGemmaForConditionalGeneration(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

PaliGemmaProcessor

class transformers.PaliGemmaProcessor

< source >

( image_processor = None tokenizer = None chat_template = None **kwargs )

Parameters

image_processor (SiglipImageProcessor, optional) — The image processor is a required input.
tokenizer (GemmaTokenizerFast, optional) — The tokenizer is a required input.
chat_template (str, optional) — A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string.

Constructs a PaliGemma processor which wraps a PaliGemma image processor and a PaliGemma tokenizer into a single processor.

PaliGemmaProcessor offers all the functionalities of SiglipImageProcessor and GemmaTokenizerFast. See the __call__() and decode() for more information.

batch_decode

< source >

( *args **kwargs )

This method forwards all its arguments to GemmaTokenizerFast’s batch_decode(). Please refer to the docstring of this method for more information.

decode

< source >

( *args **kwargs )

This method forwards all its arguments to GemmaTokenizerFast’s decode(). Please refer to the docstring of this method for more information.

PaliGemmaForConditionalGeneration

class transformers.PaliGemmaForConditionalGeneration

< source >

( config: PaliGemmaConfig )

Parameters

config (PaliGemmaConfig or PaliGemmaVisionConfig) — 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.

The PALIGEMMA model which consists of a vision backbone 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 >

( input_ids: LongTensor = None pixel_values: FloatTensor = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Union[transformers.cache_utils.Cache, typing.List[torch.FloatTensor], NoneType] = None token_type_ids: typing.Optional[torch.LongTensor] = None cache_position: typing.Optional[torch.LongTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = 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 num_logits_to_keep: int = 0 ) → transformers.models.paligemma.modeling_paligemma.PaliGemmaCausalLMOutputWithPast or tuple(torch.FloatTensor)

Parameters

input_ids (torch.LongTensor of 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.

What are input IDs?
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 [AutoImageProcessor](/docs/transformers/main/en/model_doc/auto#transformers.AutoImageProcessor). See [SiglipImageProcessor.__call__()](/docs/transformers/main/en/model_doc/imagegpt#transformers.ImageGPTFeatureExtractor.__call__) for details ([]PaliGemmaProcessor`] uses SiglipImageProcessor 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?

Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

If past_key_values is used, optionally only the last decoder_input_ids have to be input (see past_key_values).

If you want to change padding behavior, you should read modeling_opt._prepare_decoder_attention_mask and modify to your needs. See diagram 1 in the paper for more information on the default strategy.
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
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?
past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head)) and 2 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 in the cross-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.

If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).
inputs_embeds (torch.FloatTensor 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.
use_cache (bool, optional) — If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).
output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
cache_position (torch.LongTensor of shape (sequence_length), optional) — Indices depicting the position of the input sequence tokens in the sequence. Contrarily to position_ids, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length.
Args — labels (torch.LongTensor of shape (batch_size, sequence_length), optional): Labels for computing the masked language modeling loss. Indices should either be in [0, ..., config.text_config.vocab_size] or -100 (see input_ids docstring). Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.text_config.vocab_size].

num_logits_to_keep (int, optional): Calculate logits for the last num_logits_to_keep tokens. If 0, calculate logits for all input_ids (special case). Only last token logits are needed for generation, and calculating them only for that token can save memory, which becomes pretty significant for long sequences or large vocabulary size.

Returns

transformers.models.paligemma.modeling_paligemma.PaliGemmaCausalLMOutputWithPast or tuple(torch.FloatTensor)

A transformers.models.paligemma.modeling_paligemma.PaliGemmaCausalLMOutputWithPast 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 (PaliGemmaConfig) and inputs.

loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Language modeling loss (for next-token prediction).
logits (torch.FloatTensor of shape (batch_size, sequence_length, config.text_config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
past_key_values (tuple(tuple(torch.FloatTensor)), optional, returned when use_cache=True is passed or when config.use_cache=True) — Tuple of tuple(torch.FloatTensor) of length config.n_layers, with each tuple having 2 tensors of shape (batch_size, num_heads, sequence_length, embed_size_per_head))

Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see past_key_values input) to speed up sequential decoding.
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.
image_hidden_states (torch.FloatTensor, optional) — A torch.FloatTensor of size (batch_size, num_images, sequence_length, hidden_size). image_hidden_states of the model produced by the vision encoder after projecting last hidden state.

The PaliGemmaForConditionalGeneration 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.

Example:

>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, PaliGemmaForConditionalGeneration

>>> model = PaliGemmaForConditionalGeneration.from_pretrained("google/PaliGemma-test-224px-hf")
>>> processor = AutoProcessor.from_pretrained("google/PaliGemma-test-224px-hf")

>>> prompt = "answer en Where is the cow standing?"
>>> url = "https://huggingface.co./gv-hf/PaliGemma-test-224px-hf/resolve/main/cow_beach_1.png"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> inputs = processor(images=image, text=prompt,  return_tensors="pt")

>>> # Generate
>>> generate_ids = model.generate(**inputs, max_length=30)
>>> processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"answer en Where is the cow standing?\nbeach"

< > Update on GitHub

←OWLv2 Perceiver→