SmolVLM

Overview

SmolVLM2 is an adaptation of the Idefics3 model with two main differences:

It uses SmolLM2 for the text model.
It supports multi-image and video inputs

Usage tips

Input images are processed either by upsampling (if resizing is enabled) or at their original resolution. The resizing behavior depends on two parameters: do_resize and size.

Videos should not be upsampled.

If do_resize is set to True, the model resizes images so that the longest edge is 4512 pixels by default. The default resizing behavior can be customized by passing a dictionary to the size parameter. For example, `{“longest_edge”: 4 512}` is the default, but you can change it to a different value if needed.

Here’s how to control resizing and set a custom size:

image_processor = SmolVLMImageProcessor(do_resize=True, size={"longest_edge": 2 * 512}, max_image_size=512)

Additionally, the max_image_size parameter, which controls the size of each square patch the image is decomposed into, is set to 512 by default but can be adjusted as needed. After resizing (if applicable), the image processor decomposes the images into square patches based on the max_image_size parameter.

This model was contributed by orrzohar.

Usage example

Single Media inference

The model can accept both images and videos as input, but you should use only one of the modalities at a time. Here’s an example code for that.

import torch
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM2-256M-Video-Instruct")
model = AutoModelForImageTextToText.from_pretrained(
    "HuggingFaceTB/SmolVLM2-256M-Video-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="cuda"
)

conversation = [
    {
        "role": "user",
        "content":[
            {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
            {"type": "text", "text": "Describe this image."}
        ]
    }
]

inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device, dtype=torch.bfloat16)

output_ids = model.generate(**inputs, max_new_tokens=128)
generated_texts = processor.batch_decode(output_ids, skip_special_tokens=True)
print(generated_texts)


# Video
conversation = [
    {
        "role": "user",
        "content": [
            {"type": "video", "path": "/path/to/video.mp4"},
            {"type": "text", "text": "Describe this video in detail"}
        ]
    },
]

inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device, dtype=torch.bfloat16)

generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=100)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts[0])

Batch Mixed Media Inference

The model can batch inputs composed of several images/videos and text. Here is an example.

import torch
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM2-256M-Video-Instruct")
model = AutoModelForImageTextToText.from_pretrained(
    "HuggingFaceTB/SmolVLM2-256M-Video-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="cuda"
)

# Conversation for the first image
conversation1 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "path": "/path/to/image.jpg"},
            {"type": "text", "text": "Describe this image."}
        ]
    }
]

# Conversation with two images
conversation2 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "path": "/path/to/image.jpg"},
            {"type": "image", "path": "/path/to/image.jpg"},
            {"type": "text", "text": "What is written in the pictures?"}
        ]
    }
]

# Conversation with pure text
conversation3 = [
    {"role": "user","content": "who are you?"}
]


conversations = [conversation1, conversation2, conversation3]
inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device, dtype=torch.bfloat16)

generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=100)
generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_texts[0])

SmolVLMConfig

class transformers.SmolVLMConfig

< source >

( use_cache = True image_token_id = 128257 tie_word_embeddings = False vision_config = None text_config = None scale_factor = 2 pad_token_id = 128002 **kwargs )

Parameters

use_cache (bool, optional, defaults to True) — Whether or not the model should cache the key/value pairs of the attention mechanism. Only relevant if config.is_decoder=True.
image_token_id (int, optional, defaults to 128257) — The id of the “image” token.
tie_word_embeddings (bool, optional, defaults to False) — Whether or not to tie the word embeddings with the token embeddings.
vision_config (IdeficsVisionConfig or dict, optional, defaults to IdeficsVisionConfig) — Custom vision config or dict for the vision tower
text_config (PretrainedConfig or dict, optional, defaults to LlamaConfig) — Custom text config or dict for the text model
scale_factor (int, optional, defaults to 2) — The scale factor for the image encoder.
pad_token_id (int, optional, defaults to 128002) — The id of the padding token.

This is the configuration class to store the configuration of a SmolVLMModel. It is used to instantiate a SmolVLM 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 model of the SmolVLM HuggingFaceTB/SmolVLM2-2.2B-Instruct architecture.

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 SmolVLMModel, SmolVLMConfig
>>> # Initializing configuration
>>> configuration = SmolVLMConfig()
>>> # Initializing a model from the configuration
>>> model = SmolVLMModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config

SmolVLMVisionConfig

class transformers.SmolVLMVisionConfig

< source >

( hidden_size = 1152 intermediate_size = 3072 num_hidden_layers = 12 num_attention_heads = 16 num_channels = 3 image_size = 224 patch_size = 32 hidden_act = 'gelu_pytorch_tanh' layer_norm_eps = 1e-06 attention_dropout = 0.0 initializer_range = 0.02 **kwargs )

Parameters

hidden_size (int, optional, defaults to 1152) — Dimensionality of the encoder layers and the pooler layer.
intermediate_size (int, optional, defaults to 3072) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.
num_hidden_layers (int, optional, defaults to 12) — Number of hidden layers in the Transformer encoder.
num_attention_heads (int, optional, defaults to 16) — Number of attention heads for each attention layer in the Transformer encoder.
num_channels (int, optional, defaults to 3) — Number of channels in the input images.
image_size (int, optional, defaults to 224) — The size (resolution) of each image.
patch_size (int, optional, defaults to 32) — The size (resolution) of each patch.
hidden_act (str or function, optional, defaults to "gelu_pytorch_tanh") — The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "selu" and "gelu_new" "quick_gelu" are supported.
layer_norm_eps (float, optional, defaults to 1e-06) — The epsilon used by the layer normalization layers.
attention_dropout (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.

This is the configuration class to store the configuration of a SmolVLMVisionModel. It is used to instantiate a SmolVLM vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the SigLIP checkpoint google/siglip-so400m-patch14-384 used in SmolVLM HuggingFaceTB/SmolVLM2-2.2B-Instruct.

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.models.smolvlm.modeling_smolvlm import SmolVLMVisionTransformer
>>> from transformers.models.smolvlm.configuration_smolvlm import SmolVLMVisionConfig

>>> # Initializing a SmolVLMVisionConfig with google/siglip-so400m-patch14-384 style configuration
>>> configuration = SmolVLMVisionConfig()

>>> # Initializing a SmolVLMVisionTransformer (with random weights) from the google/siglip-so400m-patch14-384 style configuration
>>> model = SmolVLMVisionTransformer(configuration)

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

Idefics3VisionTransformer

class transformers.SmolVLMVisionTransformer

< source >

( config: SmolVLMVisionConfig )

Parameters

config (SmolVLMVisionConfig) — 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 SmolVLM Vision Transformer Model outputting raw image embedding. 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.

SmolVLMModel

class transformers.SmolVLMModel

< source >

( config: SmolVLMConfig )

Parameters

config (SmolVLMConfig or SmolVLMVisionConfig) — 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.

SmolVLM model consisting of a SIGLIP vision encoder and Llama3 language decoder 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.

A subclass of Idefics3Model. We do not remove or block the call to inputs_merger in forward. Instead, we override inputs_merger here with custom logic.

forward

< source >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None pixel_values: typing.Optional[torch.FloatTensor] = None pixel_attention_mask: typing.Optional[torch.BoolTensor] = None image_hidden_states: typing.Optional[torch.FloatTensor] = 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 cache_position: typing.Optional[torch.LongTensor] = None )

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?
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.
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/v4.51.1/en/model_doc/auto#transformers.AutoImageProcessor). See [CLIPImageProcessor.__call__()](/docs/transformers/v4.51.1/en/model_doc/glpn#transformers.GLPNFeatureExtractor.__call__) for details ([]LlavaProcessor`] uses CLIPImageProcessor for processing images).
pixel_attention_mask (torch.Tensor of shape (batch_size, image_size, image_size), optional) — Mask to avoid performing attention on padding pixel indices.
image_hidden_states (torch.FloatTensor of shape (batch_size, num_channels, image_size, image_size)) — The hidden states of the image encoder after modality projection.
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.

The SmolVLMModel 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.

Inputs fed to the model can have an arbitrary number of images. To account for this, pixel_values fed to the model have image padding -> (batch_size, max_num_images, 3, max_heights, max_widths) where max_num_images is the maximum number of images among the batch_size samples in the batch. Padding images are not needed beyond padding the pixel_values at the entrance of the model. For efficiency, we only pass through the vision_model’s forward the real images by discarding the padding images i.e. pixel_values of size (image_batch_size, 3, height, width) where image_batch_size would be 7 when num_images_per_sample=[1, 3, 1, 2] and max_num_images would be 3.

SmolVLMForConditionalGeneration

class transformers.SmolVLMForConditionalGeneration

< source >

( config )

Parameters

config (SmolVLMConfig or SmolVLMVisionConfig) — 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 SmolVLM Model with a language modeling head. It is made up a SigLIP vision encoder, with a language modeling head on top. 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.

A subclass of Idefics3ForConditionalGeneration that uses SmolVLMModel instead of the default Idefics3Model.

forward

< source >

( input_ids: typing.Optional[torch.LongTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None past_key_values: typing.Optional[typing.List[torch.FloatTensor]] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None pixel_values: typing.Optional[torch.FloatTensor] = None pixel_attention_mask: typing.Optional[torch.BoolTensor] = None image_hidden_states: 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 cache_position: typing.Optional[torch.LongTensor] = None return_dict: typing.Optional[bool] = None logits_to_keep: typing.Union[int, torch.Tensor] = 0 ) → transformers.models.smolvlm.modeling_smolvlm.SmolVLMCausalLMOutputWithPast 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?
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.
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/v4.51.1/en/model_doc/auto#transformers.AutoImageProcessor). See [CLIPImageProcessor.__call__()](/docs/transformers/v4.51.1/en/model_doc/glpn#transformers.GLPNFeatureExtractor.__call__) for details ([]LlavaProcessor`] uses CLIPImageProcessor for processing images).
pixel_attention_mask (torch.Tensor of shape (batch_size, image_size, image_size), optional) — Mask to avoid performing attention on padding pixel indices.
image_hidden_states (torch.FloatTensor of shape (batch_size, num_channels, image_size, image_size)) — The hidden states of the image encoder after modality projection.
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.vocab_size] or model.image_token_id (where model is your instance of SmolVLMForConditionalGeneration). Tokens with indices set to model.image_token_id are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size].

Returns

transformers.models.smolvlm.modeling_smolvlm.SmolVLMCausalLMOutputWithPast or tuple(torch.FloatTensor)

A transformers.models.smolvlm.modeling_smolvlm.SmolVLMCausalLMOutputWithPast 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 (SmolVLMConfig) 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.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 (tuple(torch.FloatTensor), optional) — Tuple of torch.FloatTensor (one for the output of the image embeddings, (batch_size, num_images, sequence_length, hidden_size). image_hidden_states of the model produced by the vision encoder

The SmolVLMForConditionalGeneration forward method, overrides the __call__ special method.

Example:

>>> import requests
>>> import torch
>>> from PIL import Image
>>> from io import BytesIO

>>> from transformers import AutoProcessor, AutoModelForImageTextToText
>>> from transformers.image_utils import load_image

>>> # Note that passing the image urls (instead of the actual pil images) to the processor is also possible
>>> image1 = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
>>> image2 = load_image("https://cdn.britannica.com/59/94459-050-DBA42467/Skyline-Chicago.jpg")
>>> image3 = load_image("https://cdn.britannica.com/68/170868-050-8DDE8263/Golden-Gate-Bridge-San-Francisco.jpg")

>>> processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM2-2.2B-Instruct")
>>> model = AutoModelForImageTextToText.from_pretrained("HuggingFaceTB/SmolVLM2-2.2B-Instruct", torch_dtype=torch.bfloat16, device_map="auto")

>>> # Create inputs
>>> messages = [
...     {
...         "role": "user",
...         "content": [
...             {"type": "video", "path": path/to/video},
...             {"type": "text", "text": "What is happening in this video?"},
...         ]
...     }
... ]

>>> inputs = processor.apply_chat_template([messages], add_generation_prompt=True)

>>> # Generate
>>> generated_ids = model.generate(**inputs, max_new_tokens=256)
>>> generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)

>>> print(generated_texts)

SmolVLMImageProcessor

class transformers.SmolVLMImageProcessor

< source >

( do_convert_rgb: bool = True do_resize: bool = True size: typing.Dict[str, int] = None resample: Resampling = <Resampling.LANCZOS: 1> do_image_splitting: bool = True max_image_size: typing.Dict[str, int] = None do_rescale: bool = True rescale_factor: float = 0.00392156862745098 do_normalize: bool = True image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_pad: bool = True **kwargs )

Parameters

do_convert_rgb (bool, optional, defaults to True) — Whether to convert the image to RGB. This is useful if the input image is of a different format e.g. RGBA. Only has an effect if the input image is in the PIL format.
do_resize (bool, optional, defaults to True) — Whether to resize the image. The longest edge of the image is resized to be <= size["longest_edge"], with the shortest edge resized to keep the input aspect ratio.
size (Dict, optional, defaults to {"longest_edge" -- 4 * 364}): Controls the size of the output image. This is a dictionary containing the key “longest_edge”. The image will be resized such that the longest edge is <= size["longest_edge"] and the shortest edge is resized to keep the input aspect ratio.
resample (Resampling, optional, defaults to Resampling.LANCZOS) — Resampling filter to use when resizing the image.
do_image_splitting (bool, optional, defaults to True) — Whether to split the image into sub-images concatenated with the original image. They are split into patches such that each patch has a size of max_image_size["height"] x max_image_size["width"].
max_image_size (Dict, optional, defaults to {"longest_edge" -- 364}): Maximum resolution of the patches of images accepted by the model. This is a dictionary containing the key “longest_edge”.
do_rescale (bool, optional, defaults to True) — Whether to rescale the image. If set to True, the image is rescaled to have pixel values between 0 and 1.
rescale_factor (float, optional, defaults to 1/255) — Rescale factor to rescale the image by if do_rescale is set to True.
do_normalize (bool, optional, defaults to True) — Whether to normalize the image. If set to True, the image is normalized to have a mean of image_mean and a standard deviation of image_std.
image_mean (float or List[float], optional, defaults to IDEFICS_STANDARD_MEAN) — Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_mean parameter in the preprocess method. Can be overridden by the image_mean parameter in the preprocess method.
image_std (float or List[float], optional, defaults to IDEFICS_STANDARD_STD) — Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_std parameter in the preprocess method. Can be overridden by the image_std parameter in the preprocess method.
do_pad (bool, optional, defaults to True) — Whether or not to pad the images to the largest height and width in the batch and number of images per sample in the batch, such that the returned tensor is of shape (batch_size, max_num_images, num_channels, max_height, max_width).

Constructs a SmolVLM image processor.

preprocess

< source >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']] do_convert_rgb: typing.Optional[bool] = None do_resize: typing.Optional[bool] = None size: typing.Optional[typing.Dict[str, int]] = None resample: Resampling = None do_image_splitting: typing.Optional[bool] = None do_rescale: typing.Optional[bool] = None max_image_size: typing.Optional[typing.Dict[str, int]] = None rescale_factor: typing.Optional[float] = None do_normalize: typing.Optional[bool] = None image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_pad: typing.Optional[bool] = None return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None return_row_col_info: bool = False data_format: typing.Optional[transformers.image_utils.ChannelDimension] = <ChannelDimension.FIRST: 'channels_first'> input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None )

Parameters

images (ImageInput) — A list of images to preprocess.
do_convert_rgb (bool, optional, defaults to self.do_convert_rgb) — Whether to convert the image to RGB.
do_resize (bool, optional, defaults to self.do_resize) — Whether to resize the image.
size (Dict[str, int], optional, defaults to self.size) — Size of the image after resizing. With the longest edge resized to keep the input aspect ratio.
resample (int, optional, defaults to self.resample) — Resampling filter to use if resizing the image. This can be one of the enum PILImageResampling. Only has an effect if do_resize is set to True.
do_image_splitting (bool, optional, defaults to self.do_image_splitting) — Whether to split the image into sub-images concatenated with the original image. They are split into patches such that each patch has a size of max_image_size["height"] x max_image_size["width"].
max_image_size (Dict, optional, defaults to self.max_image_size) — Maximum resolution of the images. If the image is larger than this size, the image is split into patches.
do_rescale (bool, optional, defaults to self.do_rescale) — Whether to rescale the image.
rescale_factor (float, optional, defaults to self.rescale_factor) — Rescale factor to rescale the image by if do_rescale is set to True.
do_normalize (bool, optional, defaults to self.do_normalize) — Whether to normalize the image.
image_mean (float or List[float], optional, defaults to self.image_mean) — Image mean to use for normalization. Only has an effect if do_normalize is set to True.
image_std (float or List[float], optional, defaults to self.image_std) — Image standard deviation to use for normalization. Only has an effect if do_normalize is set to True.
do_pad (bool, optional, defaults to self.do_pad) — Whether or not to pad the images to the largest height and width in the batch.
return_tensors (str or TensorType, optional) — The type of tensors to return. Can be one of:
- Unset: Return a list of np.ndarray.
- TensorType.TENSORFLOW or 'tf': Return a batch of type tf.Tensor.
- TensorType.PYTORCH or 'pt': Return a batch of type torch.Tensor.
- TensorType.NUMPY or 'np': Return a batch of type np.ndarray.
- TensorType.JAX or 'jax': Return a batch of type jax.numpy.ndarray.
return_row_col_info (bool, optional, default to False) — Whether to return the number of rows and columns of the split images. This is used for the SmolVLMProcessor to generate prompt strings based on the number of rows and columns.
data_format (ChannelDimension or str, optional, defaults to ChannelDimension.FIRST) — The channel dimension format for the output image. Can be one of:
- "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
- "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
- Unset: Use the channel dimension format of the input image.
input_data_format (ChannelDimension or str, optional) — The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of:
- "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
- "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
- "none" or ChannelDimension.NONE: image in (height, width) format.

Preprocess a batch of images.

SmolVLMProcessor

class transformers.SmolVLMProcessor

< source >

( image_processor tokenizer = None image_seq_len: int = 169 chat_template: typing.Optional[str] = None **kwargs )

Parameters

image_processor (SmolVLMImageProcessor) — An instance of SmolVLMImageProcessor. The image processor is a required input.
tokenizer (PreTrainedTokenizerBase, optional) — An instance of PreTrainedTokenizerBase. This should correspond with the model’s text model. The tokenizer is a required input.
image_seq_len (int, optional, defaults to 169) — The length of the image sequence i.e. the number of tokens per image in the input. This parameter is used to build the string from the input prompt and image tokens and should match the value the model used. It is computed as: image_seq_len = int(((image_size // patch_size) 2) / (scale_factor2))
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 SmolVLM processor which wraps a LLama tokenizer and SmolVLM image processor into a single processor.

SmolVLMProcessor offers all the functionalities of SmolVLMImageProcessor and SmolVLMTokenizerFast. See the docstring of call() and decode() for more information.

call

< source >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], typing.List[typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]], typing.List[typing.List[typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]]]] = None text: typing.Union[str, ForwardRef('PreTokenizedInput'), typing.List[str], typing.List[ForwardRef('PreTokenizedInput')]] = None audio = None videos: typing.Union[list['PIL.Image.Image'], ForwardRef('np.ndarray'), ForwardRef('torch.Tensor'), list['np.ndarray'], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list['np.ndarray']], list[list['torch.Tensor']]] = None **kwargs: typing_extensions.Unpack[transformers.models.smolvlm.processing_smolvlm.SmolVLMProcessorKwargs] )

Parameters

images (PIL.Image.Image, np.ndarray, torch.Tensor, List[PIL.Image.Image], List[np.ndarray], List[torch.Tensor], optional) — The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. If is of type List[ImageInput], it’s assumed that this is for a single prompt i.e. of batch size 1.
text (Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]], optional) — The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set is_split_into_words=True (to lift the ambiguity with a batch of sequences). Wherever an image token, <image> is encountered it is expanded to <fake_token_around_image> + <row_x_col_y> + <image> image_seq_len `.
return_tensors (Union[str, TensorType], optional) — If set, will return tensors of a particular framework. See PreTrainedTokenizerFast.call() for more information.

Processes the input prompts and returns a BatchEncoding.

Example:

>>> import requests
>>> from transformers import SmolVLMProcessor
>>> from transformers.image_utils import load_image

>>> processor = SmolVLMProcessor.from_pretrained("HuggingFaceM4/SmolVLM2-256M-Video-Instruct")
>>> processor.image_processor.do_image_splitting = False  # Force as False to simplify the example

>>> url1 = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
>>> url2 = "https://cdn.britannica.com/59/94459-050-DBA42467/Skyline-Chicago.jpg"

>>> image1, image2 = load_image(url1), load_image(url2)
>>> images = [[image1], [image2]]

>>> text = [
...     "<image>In this image, we see",
...     "bla bla bla<image>",
... ]
>>> outputs = processor(images=images, text=text, return_tensors="pt", padding=True)
>>> input_ids = outputs.input_ids
>>> input_tokens = processor.tokenizer.batch_decode(input_ids)
>>> print(input_tokens)
['<|begin_of_text|><fake_token_around_image><global-img>((<image>)*169)<fake_token_around_image> In this image, we see', '<|reserved_special_token_0|><|reserved_special_token_0|><|reserved_special_token_0|><|begin_of_text|>bla bla bla<fake_token_around_image><global-img>((<image>)*169)<fake_token_around_image>']

< > Update on GitHub

Transformers

SmolVLM

Overview

Usage tips

Usage example

Single Media inference

Batch Mixed Media Inference

SmolVLMConfig

class transformers.SmolVLMConfig

SmolVLMVisionConfig

class transformers.SmolVLMVisionConfig

Idefics3VisionTransformer

class transformers.SmolVLMVisionTransformer

SmolVLMModel

class transformers.SmolVLMModel

forward

SmolVLMForConditionalGeneration

class transformers.SmolVLMForConditionalGeneration

forward

SmolVLMImageProcessor

class transformers.SmolVLMImageProcessor

preprocess

SmolVLMProcessor

class transformers.SmolVLMProcessor

__call__

call