4.65 TB
9,501 files
Updated 23 days ago
Name
Size
CoSyn_400k_chart
CoSyn_400k_chemical
CoSyn_400k_circuit
CoSyn_400k_diagram
CoSyn_400k_document
CoSyn_400k_graphic
CoSyn_400k_math
CoSyn_400k_music
CoSyn_400k_nutrition
CoSyn_400k_table
DoclingMatix
LLaVA_Instruct_150K
SynthChartNet
SynthCodeNet
SynthFormulaNet
Unichart
a_okvqa
aguvis-stage-1
ai2d_merged
alfworldgpt
allava_laion
allava_vflan
aokvqa
art
arxivqa
bentham
blockdiagramcomputerized
blockdiagramhandwritten
cambrian(filtered)_processed
captcha
chart2text
chartqa
chinesememe
chrome_writting
clevr
clevr_math
clevr_math(mathv360k)
coco_colors
cocoqa
cocotext
ctw
datik
datikz
densefusion_1m
diagram_image_to_text
docvqa
drivelm
dvqa
est_vqa
face_emotion
figureqa
figureqa(mathv360k)
finqa
funsd
geo170k(align)
geo170k(qa)
geo3k
geometry3k(mathv360k)
geomverse
geoqa+(mathv360k)
geos(mathv360k)
google_landmarks
groundui
handwriting_forms
hateful_memes
hitab
hme100k
hw_squad
iam
iconqa
iconqa(mathv360k)
idk
iiit5k
image_textualization(filtered)
imgur5k
indoor_qa
infographic(gpt4v)
infographic_vqa
infographic_vqa_llava_format
intergps
invoices_receipts
k12_printing
laion_gpt4v
latex_handwritten
latexformulas
llavar_gpt4_20k
lnqa
localized_narratives
lrv_chart
lrv_normal(filtered)
lvis_instruct4v
mapqa
mapqa(mathv360k)
maptext
mathwriting-google
mavis_math_metagen
mavis_math_rule_geo
memotion
.gitattributes2.46 kB
xet
README.md152 kB
xet
README.md

Fine Vision

image/png

FineVision is a massive collection of datasets with 17.3M images, 24.3M samples, 88.9M turns, and 9.5B answer tokens, designed for training state-of-the-art open Vision-Language-Models.

More detail can be found in the blog post: https://huggingface.co/spaces/HuggingFaceM4/FineVision

Load the data

  from datasets import load_dataset, get_dataset_config_names

  # Get all subset names and load the first one
  available_subsets = get_dataset_config_names('HuggingFaceM4/FineVision')
  ds = load_dataset('HuggingFaceM4/FineVision', name=available_subsets[0], split='train', streaming=True)
  
  # Inspect the first sample
  ds[0]

Structure

{
  'images': [<PIL.PngImagePlugin.PngImageFile image mode=RGB size=387x194 at 0x7F8F0B308200>],
  'texts': [{'user': 'Question: What is between the reticulum and the abomasum?\nChoices:\nA. Intestine\nB. Omasum\nC. Stomach\nD. Rumen\nAnswer with the letter.', 'assistant': 'Answer: B'},
            {'user': 'Here is a diagram figure extracted from some Grade 1 - 6 science books.\nPlease first describe the content of this figure in detail, including how the knowledge visually displayed in the diagram.\nThen start with a section title "related knowledge:", briefly and concisely highlight the related domain knowledge and theories that underly this diagram. Note that you do not need to provide much detail. Simply cover the most important concepts.', 'assistant': "The figure is a simple diagram of the four compartments of a ruminant animal's stomach, which are the rumen, reticulum, omasum, and abomasum. The diagram shows the relative size and position of each compartment within the stomach, with arrows indicating the direction of food flow from one compartment to the next. \n\nRelated Knowledge:\n- Ruminant Digestion: Ruminants such as cows, sheep, and goats have a unique digestive system that allows them to break down fibrous plant material, like grass, that other animals cannot digest.\n- Four Stomach Compartments: The rumen is the largest compartment and serves as a fermentation vat where microbes break down fibrous material. The reticulum traps foreign objects and also helps in fermentation. The omasum absorbs water and nutrients, and the abomasum is the true stomach where digestion occurs similarly to monogastric animals.\n- Microbial Fermentation: The microbes in the rumen produce volatile fatty acids which are the primary energy source for ruminants. They also produce gases like methane, which are eructated (belched) out.\n- Ruminant Nutrition: Ruminants rely on a high-fiber diet and have to consume large quantities of forage to meet their nutritional needs."}],
  'source': 'original',
  'image_correspondence_ratings': [4, 3],
  'image_correspondence_min': 3,
  'visual_dependency_ratings': [4, 5],
  'visual_dependency_min': 4,
  'formatting_ratings': [4, 4],
  'formatting_min': 4,
  'relevance_ratings': [5, 5],
  'relevance_min': 5
}

Categories

image/png

Licensing Information

Each of the publicly available sub-datasets present in FineVision are governed by specific licensing conditions. Therefore, when making use of them you must take into consideration each of the licenses governing each dataset. To the extent we have any rights in the prompts, these are licensed under CC-BY-4.0.

Citation

If you find this dataset useful, please cite:

@misc{wiedmann2025finevisionopendataneed,
      title={FineVision: Open Data Is All You Need}, 
      author={Luis Wiedmann and Orr Zohar and Amir Mahla and Xiaohan Wang and Rui Li and Thibaud Frere and Leandro von Werra and Aritra Roy Gosthipaty and Andrés Marafioti},
      year={2025},
      eprint={2510.17269},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2510.17269}, 
}
Total size
4.65 TB
Files
9,501
Last updated
Jun 29
Pre-warmed CDN
US EU US EU

Contributors