Hugging Face's logo

Transformers documentation

LightOnOcr

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v5.0.0rc2).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

This model was released on {release_date} and added to Hugging Face Transformers on 2026-01-14.

LightOnOcr

LightOnOcr is a compact, end-to-end vision–language model for Optical Character Recognition (OCR) and document understanding. It achieves state-of-the-art accuracy in its weight class while being several times faster and cheaper than larger general-purpose VLMs.

📝 Read the full blog post | 📓 Finetuning notebook

Model Overview

LightOnOcr combines a Vision Transformer encoder (Pixtral-based) with a lightweight text decoder (Qwen3-based) distilled from high-quality open VLMs. It is optimized for document parsing tasks, producing accurate, layout-aware text extraction from high-resolution pages.

Usage

import torch

from transformers import LightOnOcrForConditionalGeneration, LightOnOcrProcessor


device = "mps" if torch.backends.mps.is_available() else "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float32 if device == "mps" else torch.bfloat16

model = LightOnOcrForConditionalGeneration.from_pretrained("lightonai/LightOnOCR-1B-1025", dtype=dtype).to(
    device
)
processor = LightOnOcrProcessor.from_pretrained("lightonai/LightOnOCR-1B-1025")

url = "https://huggingface.co/datasets/hf-internal-testing/fixtures_ocr/resolve/main/SROIE-receipt.jpeg"

conversation = [{"role": "user", "content": [{"type": "image", "url": url}]}]

inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
)
inputs = {k: v.to(device=device, dtype=dtype) if v.is_floating_point() else v.to(device) for k, v in inputs.items()}

output_ids = model.generate(**inputs, max_new_tokens=1024)
generated_ids = output_ids[0, inputs["input_ids"].shape[1] :]
output_text = processor.decode(generated_ids, skip_special_tokens=True)
print(output_text)

LightOnOcrConfig

class transformers.LightOnOcrConfig

< >

( spatial_merge_size: int = 2 image_token_id: int = 151655 tie_word_embeddings: bool = True vision_config: dict[str, typing.Any] | None = None text_config: dict[str, typing.Any] | None = None **kwargs )

Parameters

  • spatial_merge_size (int, optional, defaults to 2) — The size of spatial merging for image patches.
  • image_token_id (int, optional, defaults to 151655) — The id of the image token in the vocabulary.
  • tie_word_embeddings (bool, optional, defaults to True) — Whether the model’s input and output word embeddings should be tied.
  • vision_config (dict or LightOnOcrVisionConfig, optional) — Custom vision configuration or dictionary with vision configuration values.
  • text_config (dict or LightOnOcrTextConfig, optional) — Custom text configuration or dictionary with text configuration values.

This is the configuration class to store the configuration of a LightOnOcrForConditionalGeneration. It is used to instantiate a LightOnOcr model according to the specified arguments, defining the model architecture.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information. Instantiating a configuration with the defaults will yield a similar configuration to that of the LightOnOcr lightonocr-hf/lightonocr-9b architecture.

Example:

>>> from transformers import LightOnOcrConfig, LightOnOcrForConditionalGeneration

>>> # Initializing a LightOnOcr configuration
>>> configuration = LightOnOcrConfig()

>>> # Initializing a model from the configuration
>>> model = LightOnOcrForConditionalGeneration(configuration)

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

LightOnOcrProcessor

class transformers.LightOnOcrProcessor

< >

( image_processor = None tokenizer = None patch_size: int = 14 spatial_merge_size: int = 2 chat_template = None **kwargs )

__call__

< >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None text: str | list[str] | list[list[str]] = None **kwargs: typing_extensions.Unpack[transformers.models.lighton_ocr.processing_lighton_ocr.LightOnOcrProcessorKwargs] )

LightOnOcrModel

class transformers.LightOnOcrModel

< >

( config: LightOnOcrConfig )

Parameters

  • config (LightOnOcrConfig) — 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 LightOnOcr model which consists of a vision backbone and a language model, without a language modeling head.

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

< >

( input_ids: torch.LongTensor | None = None pixel_values: torch.FloatTensor | None = None attention_mask: torch.Tensor | None = None position_ids: torch.LongTensor | None = None past_key_values: transformers.cache_utils.Cache | None = None inputs_embeds: torch.FloatTensor | None = None use_cache: bool | None = None output_attentions: bool | None = None output_hidden_states: bool | None = None return_dict: bool | None = None cache_position: torch.LongTensor | None = None image_sizes: torch.Tensor | None = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.models.lighton_ocr.modeling_lighton_ocr.LightOnOcrModelOutputWithPast or tuple(torch.FloatTensor)

Parameters

  • input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

    Indices can be obtained using AutoTokenizer. 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), optional) — The tensors corresponding to the input images. Pixel values can be obtained using PixtralImageProcessorFast. See PixtralImageProcessorFast.call() for details (LightOnOcrProcessor uses PixtralImageProcessorFast 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?

  • 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 (~cache_utils.Cache, optional) — Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the past_key_values returned by the model at a previous stage of decoding, when use_cache=True or config.use_cache=True.

    Only Cache instance is allowed as input, see our kv cache guide. If no past_key_values are passed, DynamicCache will be initialized by default.

    The model will output the same cache format that is fed as input.

    If past_key_values are used, the user is expected to input only unprocessed input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, unprocessed_length) instead of all 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.
  • image_sizes (torch.Tensor of shape (batch_size, 2), optional) — The sizes of the images in the batch, being (height, width) for each image.

Returns

transformers.models.lighton_ocr.modeling_lighton_ocr.LightOnOcrModelOutputWithPast or tuple(torch.FloatTensor)

A transformers.models.lighton_ocr.modeling_lighton_ocr.LightOnOcrModelOutputWithPast 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 (LightOnOcrConfig) and inputs.

  • last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the model.

  • past_key_values (Cache, optional, returned when use_cache=True is passed or when config.use_cache=True) — It is a Cache instance. For more details, see our kv cache guide.

    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, 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, 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 and after projecting the last hidden state.

The LightOnOcrModel 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.

LightOnOcrForConditionalGeneration

class transformers.LightOnOcrForConditionalGeneration

< >

( config: LightOnOcrConfig )

Parameters

  • config (LightOnOcrConfig) — 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 LIGHTON_OCR 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

< >

( input_ids: torch.LongTensor | None = None pixel_values: torch.FloatTensor | None = None attention_mask: torch.Tensor | None = None position_ids: torch.LongTensor | None = None past_key_values: transformers.cache_utils.Cache | None = None inputs_embeds: torch.FloatTensor | None = None labels: torch.LongTensor | None = None use_cache: bool | None = None output_attentions: bool | None = None output_hidden_states: bool | None = None return_dict: bool | None = None cache_position: torch.LongTensor | None = None logits_to_keep: int | torch.Tensor = 0 image_sizes: torch.Tensor | None = None **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → transformers.models.lighton_ocr.modeling_lighton_ocr.LightOnOcrCausalLMOutputWithPast or tuple(torch.FloatTensor)

Parameters

  • input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

    Indices can be obtained using AutoTokenizer. 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), optional) — The tensors corresponding to the input images. Pixel values can be obtained using PixtralImageProcessorFast. See PixtralImageProcessorFast.call() for details (LightOnOcrProcessor uses PixtralImageProcessorFast 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?

  • 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 (~cache_utils.Cache, optional) — Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the past_key_values returned by the model at a previous stage of decoding, when use_cache=True or config.use_cache=True.

    Only Cache instance is allowed as input, see our kv cache guide. If no past_key_values are passed, DynamicCache will be initialized by default.

    The model will output the same cache format that is fed as input.

    If past_key_values are used, the user is expected to input only unprocessed input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, unprocessed_length) instead of all 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.
  • 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 -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.vocab_size].
  • 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.
  • logits_to_keep (Union[int, torch.Tensor], optional, defaults to 0) — 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).
  • image_sizes (torch.Tensor of shape (batch_size, 2), optional) — The sizes of the images in the batch, being (height, width) for each image.

Returns

transformers.models.lighton_ocr.modeling_lighton_ocr.LightOnOcrCausalLMOutputWithPast or tuple(torch.FloatTensor)

A transformers.models.lighton_ocr.modeling_lighton_ocr.LightOnOcrCausalLMOutputWithPast 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 (LightOnOcrConfig) 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 (Cache, optional, returned when use_cache=True is passed or when config.use_cache=True) — It is a Cache instance. For more details, see our kv cache guide.

    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] | None.hidden_states, 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] | None.attentions, 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 and after projecting the last hidden state.

The LightOnOcrForConditionalGeneration 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, LightOnOcrForConditionalGeneration

>>> model = LightOnOcrForConditionalGeneration.from_pretrained("mistralai/Mistral-Small-3.1-24B-Instruct-2503")
>>> processor = AutoProcessor.from_pretrained("mistralai/Mistral-Small-3.1-24B-Instruct-2503")

>>> prompt = "<s>[INST][IMG]What is the image?[/INST]"
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> 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_new_tokens=15)
>>> processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"What is the image?The image depicts two cats lying on a pink blanket."
Update on GitHub

←LFM2-VL LiLT→