PaliGemma

PaliGemma is a family of vision-language models (VLMs), combining SigLIP with the Gemma 2B model. PaliGemma is available in 3B, 10B, and 28B parameters. The main purpose of PaliGemma is to provide an adaptable base VLM that is easy to transfer to other tasks. The SigLIP vision encoder is a “shape optimized” contrastively pretrained ViT that converts an image into a sequence of tokens and prepended to an optional prompt. The Gemma 2B model is used as the decoder. PaliGemma uses full attention on all image and text tokens to maximize its capacity.

PaliGemma 2 improves on the first model by using Gemma 2 (2B, 9B, and 27B parameter variants) as the decoder. These are available as pt or mix variants. The pt checkpoints are intended for further fine-tuning and the mix checkpoints are ready for use out of the box.

You can find all the original PaliGemma checkpoints under the PaliGemma, PaliGemma 2, and PaliGemma 2 Mix collections.

Click on the PaliGemma models in the right sidebar for more examples of how to apply PaliGemma to different vision and language tasks.

The example below demonstrates how to generate text based on an image with Pipeline or the AutoModel class.

Pipeline

AutoModel

Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the Quantization overview for more available quantization backends.

The example below uses torchao to only quantize the weights to int4.

# pip install torchao
import torch
import requests
from PIL import Image
from transformers import TorchAoConfig, AutoProcessor, PaliGemmaForConditionalGeneration

quantization_config = TorchAoConfig("int4_weight_only", group_size=128)
model = PaliGemmaForConditionalGeneration.from_pretrained(
    "google/paligemma2-28b-mix-224",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    quantization_config=quantization_config
)
processor = AutoProcessor.from_pretrained(
    "google/paligemma2-28b-mix-224",
)

prompt = "What is in this image?"
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(image, prompt, return_tensors="pt").to("cuda")

output = model.generate(**inputs, max_new_tokens=50, cache_implementation="static")
print(processor.decode(output[0], skip_special_tokens=True))

Use the AttentionMaskVisualizer to better understand what tokens the model can and cannot attend to.

from transformers.utils.attention_visualizer import AttentionMaskVisualizer

visualizer = AttentionMaskVisualizer("google/paligemma2-3b-mix-224")
visualizer("<img> What is in this image?")

Notes

PaliGemma is not a conversational model and works best when fine-tuned for specific downstream tasks such as image captioning, visual question answering (VQA), object detection, and document understanding.
PaliGemmaProcessor can prepare images, text, and optional labels for the model. Pass the suffix parameter to the processor to create labels for the model during fine-tuning.
```
prompt = "What is in this image?"
answer = "a pallas cat"
inputs = processor(images=image, text=prompt, suffix=answer, return_tensors="pt")
```

PaliGemma can support multiple input images if it is fine-tuned to accept multiple images. For example, the NLVR2 checkpoint supports multiple images. Pass the images as a list to the processor.

import torch
import requests
from PIL import Image
from transformers import TorchAoConfig, AutoProcessor, PaliGemmaForConditionalGeneration

model = PaliGemmaForConditionalGeneration.from_pretrained("google/paligemma-3b-ft-nlvr2-448")
processor = AutoProcessor.from_pretrained("google/paligemma-3b-ft-nlvr2-448")

prompt = "Are these two images the same?"
cat_image = Image.open(
    requests.get("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg", stream=True).raw
)
cow_image = Image.open(
    requests.get(
        "https://media.istockphoto.com/id/1192867753/photo/cow-in-berchida-beach-siniscola.jpg?s=612x612&w=0&k=20&c=v0hjjniwsMNfJSuKWZuIn8pssmD5h5bSN1peBd1CmH4=", stream=True
    ).raw
)

inputs = processor(images=[[cat_image, cow_image]], text=prompt, return_tensors="pt")

output = model.generate(**inputs, max_new_tokens=20, cache_implementation="static")
print(processor.decode(output[0], skip_special_tokens=True))

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[typing.List[torch.FloatTensor], transformers.cache_utils.Cache, 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 logits_to_keep: typing.Union[int, torch.Tensor] = 0 **lm_kwargs ) → 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/vilt#transformers.ViltFeatureExtractor.__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.
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].
logits_to_keep (int or torch.Tensor, optional) — If an int, compute logits for the last 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. If a torch.Tensor, must be 1D corresponding to the indices to keep in the sequence length dimension. This is useful when using packed tensor format (single dimension for batch and sequence length).

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/paligemma2-3b-mix-224")
>>> processor = AutoProcessor.from_pretrained("google/paligemma2-3b-mix-224")

>>> prompt = "Where is the cat standing?"
>>> url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
>>> image = Image.open(requests.get(url, stream=True).raw)

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

>>> # Generate
>>> generate_ids = model.generate(**inputs,)
>>> processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"Where is the cat standing?\nsnow"

< > Update on GitHub

Transformers

PaliGemma

Notes

PaliGemmaConfig

class transformers.PaliGemmaConfig

PaliGemmaProcessor

class transformers.PaliGemmaProcessor

batch_decode

decode

PaliGemmaForConditionalGeneration

class transformers.PaliGemmaForConditionalGeneration

forward