librarian-bots/dataset_cards_with_metadata

datasetId large_stringlengths 6 116	author large_stringlengths 2 42	last_modified large_stringdate 2021-04-29 15:34:29 2025-08-18 20:14:01	downloads int64 0 3.97M	likes int64 0 7.74k	tags large listlengths 1 7.92k	task_categories large listlengths 0 48	createdAt large_stringdate 2022-03-02 23:29:22 2025-08-18 20:11:48	trending_score float64 0 64	card large_stringlengths 31 1.01M
junnystateofmind/testing_refuel_5_turns_only_ckp_1	junnystateofmind	2024-11-23T14:42:02Z	14	0	[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2024-11-23T14:42:00Z	0	--- dataset_info: features: - name: combined_data struct: - name: narrative dtype: string - name: trajectory list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 37130 num_examples: 5 download_size: 20861 dataset_size: 37130 configs: - config_name: default data_files: - split: train path: data/train-* ---
dsrtrain/qwq2ep_raft_iter1_gen_with_rewards	dsrtrain	2025-02-12T18:37:22Z	16	0	[ "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-02-12T18:37:01Z	0	--- dataset_info: features: - name: idx dtype: int64 - name: prompt dtype: string - name: answers sequence: string - name: gt struct: - name: ground_truth dtype: string - name: style dtype: string - name: rewards sequence: bool splits: - name: train num_bytes: 1010939991 num_examples: 20000 download_size: 373038950 dataset_size: 1010939991 configs: - config_name: default data_files: - split: train path: data/train-* ---
mlfoundations-dev/d1_math_multiple_languages_10k	mlfoundations-dev	2025-05-01T16:33:51Z	0	0	[ "size_categories:1K<n<10K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-05-01T16:28:39Z	0	--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: instruction_seed dtype: string - name: response_seed dtype: string - name: _source dtype: string - name: gpt41_mini_response dtype: string - name: __original_row_idx dtype: int64 - name: length dtype: int64 - name: ms_id dtype: int64 - name: reasoning sequence: string - name: deepseek_solution sequence: string - name: final_reasoning_trace sequence: string - name: correct sequence: bool - name: classifier_reasoning dtype: string - name: _majority_responses sequence: string - name: verified_final_reasoning_trace dtype: string - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 18188281981.012657 num_examples: 10000 download_size: 7437623502 dataset_size: 18188281981.012657 configs: - config_name: default data_files: - split: train path: data/train-* ---
mlazniewski/mlazniewski_octopus_train_cellines	mlazniewski	2025-06-06T12:25:18Z	0	0	[ "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-06-06T12:25:02Z	0	--- dataset_info: - config_name: disease_questions features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 324497 num_examples: 2254 download_size: 66737 dataset_size: 324497 - config_name: lineage_questions features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 536022 num_examples: 3940 download_size: 106817 dataset_size: 536022 - config_name: mutations_questions features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 491417 num_examples: 3050 download_size: 97498 dataset_size: 491417 - config_name: site_questions features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 477375 num_examples: 3942 download_size: 102655 dataset_size: 477375 - config_name: transformant_questions features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 47084 num_examples: 340 download_size: 11198 dataset_size: 47084 configs: - config_name: disease_questions data_files: - split: train path: disease_questions/train-* - config_name: lineage_questions data_files: - split: train path: lineage_questions/train-* - config_name: mutations_questions data_files: - split: train path: mutations_questions/train-* - config_name: site_questions data_files: - split: train path: site_questions/train-* - config_name: transformant_questions data_files: - split: train path: transformant_questions/train-* ---
emrecn/ShortData	emrecn	2025-05-16T13:03:57Z	0	0	[ "size_categories:100K<n<1M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-05-16T08:35:23Z	0	--- dataset_info: features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 24684536649.125 num_examples: 299967 download_size: 24646621713 dataset_size: 24684536649.125 configs: - config_name: default data_files: - split: train path: data/train-* ---
colabfit/HME21_train	colabfit	2025-05-14T01:49:50Z	0	0	[ "license:cc-by-4.0", "region:us", "molecular dynamics", "mlip", "interatomic potential" ]	[]	2025-05-14T01:49:48Z	0	--- configs: - config_name: default data_files: "main/*.parquet" license: cc-by-4.0 tags: - molecular dynamics - mlip - interatomic potential pretty_name: HME21 train --- ### Cite this dataset Takamoto, S., Shinagawa, C., Motoki, D., Nakago, K., Li, W., Kurata, I., Watanabe, T., Yayama, Y., Iriguchi, H., Asano, Y., Onodera, T., Ishii, T., Kudo, T., Ono, H., Sawada, R., Ishitani, R., Ong, M., Yamaguchi, T., Kataoka, T., Hayashi, A., Charoenphakdee, N., and Ibuka, T. _HME21 train_. ColabFit, 2023. https://doi.org/10.60732/845cc1b5 ### View on the ColabFit Exchange https://materials.colabfit.org/id/DS_jhfis7syauhm_0 # Dataset Name HME21 train ### Description The training set from HME21. The high-temperature multi-element 2021 (HME21) dataset comprises approximately 25,000 configurations, including 37 elements, used in the training of a universal NNP called PreFerential Potential (PFP). The dataset specifically contains disordered and unstable structures, and structures that include irregular substitutions, as well as varied temperature and density. <br>Additional details stored in dataset columns prepended with "dataset_". ### Dataset authors So Takamoto, Chikashi Shinagawa, Daisuke Motoki, Kosuke Nakago, Wenwen Li, Iori Kurata, Taku Watanabe, Yoshihiro Yayama, Hiroki Iriguchi, Yusuke Asano, Tasuku Onodera, Takafumi Ishii, Takao Kudo, Hideki Ono, Ryohto Sawada, Ryuichiro Ishitani, Marc Ong, Taiki Yamaguchi, Toshiki Kataoka, Akihide Hayashi, Nontawat Charoenphakdee, Takeshi Ibuka ### Publication https://doi.org/10.1038/s41467-022-30687-9 ### Original data link https://doi.org/10.6084/m9.figshare.19658538.v2 ### License CC-BY-4.0 ### Number of unique molecular configurations 19956 ### Number of atoms 555050 ### Elements included Pb, Ba, Co, Cr, Cu, Mg, Mn, Mo, Ni, O, S, Sc, Si, V, Zn, Fe, Ir, Li, P, Pt, Ru, Sn, Ca, F, Au, Cl, H, Ag, C, In, K, N, Pd, Rh, Na, Ti, Al ### Properties included energy, atomic forces, cauchy stress
abhinav302019/olympiad_data_296	abhinav302019	2025-03-05T15:32:01Z	18	0	[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-03-05T15:31:58Z	0	--- dataset_info: features: - name: problem dtype: string - name: Known_Solution dtype: string - name: Known_Answer dtype: string - name: Generated_Solution dtype: string - name: Generated_Answer dtype: string - name: Judge_Evaluation dtype: string - name: Judge_Rating dtype: string - name: Judge_Justification dtype: string splits: - name: train num_bytes: 81293 num_examples: 10 download_size: 48130 dataset_size: 81293 configs: - config_name: default data_files: - split: train path: data/train-* ---
yasserrmd/food-safety-classifications	yasserrmd	2025-01-06T04:33:24Z	48	1	[ "language:en", "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "library:distilabel", "region:us", "synthetic", "distilabel", "rlaif", "datacraft" ]	[]	2025-01-04T06:49:56Z	0	--- language: - en size_categories: n<1K dataset_info: features: - name: text dtype: string - name: label dtype: class_label: names: '0': food-safety '1': non-food-safety splits: - name: train num_bytes: 76322 num_examples: 439 download_size: 34724 dataset_size: 76322 configs: - config_name: default data_files: - split: train path: data/train-* tags: - synthetic - distilabel - rlaif - datacraft --- <p align="left"> <a href="https://github.com/argilla-io/distilabel"> <img src="https://raw.githubusercontent.com/argilla-io/distilabel/main/docs/assets/distilabel-badge-light.png" alt="Built with Distilabel" width="200" height="32"/> </a> </p> # Dataset Card for my-distiset-8c05c9f2 This dataset has been created with [distilabel](https://distilabel.argilla.io/). ## Dataset Summary This dataset contains a `pipeline.yaml` which can be used to reproduce the pipeline that generated it in distilabel using the `distilabel` CLI: ```console distilabel pipeline run --config "https://huggingface.co/datasets/yasserrmd/my-distiset-8c05c9f2/raw/main/pipeline.yaml" ``` or explore the configuration: ```console distilabel pipeline info --config "https://huggingface.co/datasets/yasserrmd/my-distiset-8c05c9f2/raw/main/pipeline.yaml" ``` ## Dataset structure The examples have the following structure per configuration: <details><summary> Configuration: default </summary><hr> ```json { "label": 0, "text": "It\u0027s okay to leave leftovers at room temperature for up to 2 hours before refrigerating them." } ``` This subset can be loaded as: ```python from datasets import load_dataset ds = load_dataset("yasserrmd/my-distiset-8c05c9f2", "default") ``` Or simply as it follows, since there's only one configuration and is named `default`: ```python from datasets import load_dataset ds = load_dataset("yasserrmd/my-distiset-8c05c9f2") ``` </details>
ErikaaWang/oasst1_highqual_ift	ErikaaWang	2024-12-19T10:30:39Z	44	0	[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2024-12-19T10:30:31Z	0	--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train_sft num_bytes: 5024033 num_examples: 3463 - name: test_sft num_bytes: 259338 num_examples: 186 download_size: 3091231 dataset_size: 5283371 configs: - config_name: default data_files: - split: train_sft path: data/train_sft-* - split: test_sft path: data/test_sft-* ---
mahdiR128/fiting_clothes_in_body_2	mahdiR128	2024-11-26T15:05:18Z	15	0	[ "size_categories:n<1K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2024-11-26T15:03:00Z	0	--- dataset_info: features: - name: image dtype: image - name: text dtype: string splits: - name: train num_bytes: 3613862.0 num_examples: 7 download_size: 3614947 dataset_size: 3613862.0 configs: - config_name: default data_files: - split: train path: data/train-* ---
mteb/CUADJointIPOwnershipLegalBenchClassification	mteb	2025-05-06T11:54:36Z	0	0	[ "task_categories:text-classification", "annotations_creators:expert-annotated", "multilinguality:monolingual", "language:eng", "license:cc-by-4.0", "modality:text", "arxiv:2308.11462", "arxiv:2103.06268", "arxiv:2502.13595", "arxiv:2210.07316", "region:us", "mteb", "text" ]	[ "text-classification" ]	2025-05-06T11:54:32Z	0	--- annotations_creators: - expert-annotated language: - eng license: cc-by-4.0 multilinguality: monolingual task_categories: - text-classification task_ids: [] dataset_info: features: - name: text dtype: string - name: label dtype: int64 splits: - name: train num_bytes: 4431 num_examples: 6 - name: test num_bytes: 74151 num_examples: 192 download_size: 49562 dataset_size: 78582 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* tags: - mteb - text --- <!-- adapted from https://github.com/huggingface/huggingface_hub/blob/v0.30.2/src/huggingface_hub/templates/datasetcard_template.md --> <div align="center" style="padding: 40px 20px; background-color: white; border-radius: 12px; box-shadow: 0 2px 10px rgba(0, 0, 0, 0.05); max-width: 600px; margin: 0 auto;"> <h1 style="font-size: 3.5rem; color: #1a1a1a; margin: 0 0 20px 0; letter-spacing: 2px; font-weight: 700;">CUADJointIPOwnershipLegalBenchClassification</h1> <div style="font-size: 1.5rem; color: #4a4a4a; margin-bottom: 5px; font-weight: 300;">An <a href="https://github.com/embeddings-benchmark/mteb" style="color: #2c5282; font-weight: 600; text-decoration: none;" onmouseover="this.style.textDecoration='underline'" onmouseout="this.style.textDecoration='none'">MTEB</a> dataset</div> <div style="font-size: 0.9rem; color: #2c5282; margin-top: 10px;">Massive Text Embedding Benchmark</div> </div> This task was constructed from the CUAD dataset. It consists of determining if the clause provides for joint or shared ownership of intellectual property between the parties to the contract. \| \| \| \|---------------\|---------------------------------------------\| \| Task category \| t2c \| \| Domains \| Legal, Written \| \| Reference \| https://huggingface.co/datasets/nguha/legalbench \| ## How to evaluate on this task You can evaluate an embedding model on this dataset using the following code: ```python import mteb task = mteb.get_tasks(["CUADJointIPOwnershipLegalBenchClassification"]) evaluator = mteb.MTEB(task) model = mteb.get_model(YOUR_MODEL) evaluator.run(model) ``` <!-- Datasets want link to arxiv in readme to autolink dataset with paper --> To learn more about how to run models on `mteb` task check out the [GitHub repitory](https://github.com/embeddings-benchmark/mteb). ## Citation If you use this dataset, please cite the dataset as well as [mteb](https://github.com/embeddings-benchmark/mteb), as this dataset likely includes additional processing as a part of the [MMTEB Contribution](https://github.com/embeddings-benchmark/mteb/tree/main/docs/mmteb). ```bibtex @misc{guha2023legalbench, archiveprefix = {arXiv}, author = {Neel Guha and Julian Nyarko and Daniel E. Ho and Christopher Ré and Adam Chilton and Aditya Narayana and Alex Chohlas-Wood and Austin Peters and Brandon Waldon and Daniel N. Rockmore and Diego Zambrano and Dmitry Talisman and Enam Hoque and Faiz Surani and Frank Fagan and Galit Sarfaty and Gregory M. Dickinson and Haggai Porat and Jason Hegland and Jessica Wu and Joe Nudell and Joel Niklaus and John Nay and Jonathan H. Choi and Kevin Tobia and Margaret Hagan and Megan Ma and Michael Livermore and Nikon Rasumov-Rahe and Nils Holzenberger and Noam Kolt and Peter Henderson and Sean Rehaag and Sharad Goel and Shang Gao and Spencer Williams and Sunny Gandhi and Tom Zur and Varun Iyer and Zehua Li}, eprint = {2308.11462}, primaryclass = {cs.CL}, title = {LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models}, year = {2023}, } @article{hendrycks2021cuad, author = {Hendrycks, Dan and Burns, Collin and Chen, Anya and Ball, Spencer}, journal = {arXiv preprint arXiv:2103.06268}, title = {Cuad: An expert-annotated nlp dataset for legal contract review}, year = {2021}, } @article{enevoldsen2025mmtebmassivemultilingualtext, title={MMTEB: Massive Multilingual Text Embedding Benchmark}, author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Michail and John Yang and Manuel Faysse and Aleksei Vatolin and Nandan Thakur and Manan Dey and Dipam Vasani and Pranjal Chitale and Simone Tedeschi and Nguyen Tai and Artem Snegirev and Michael Günther and Mengzhou Xia and Weijia Shi and Xing Han Lù and Jordan Clive and Gayatri Krishnakumar and Anna Maksimova and Silvan Wehrli and Maria Tikhonova and Henil Panchal and Aleksandr Abramov and Malte Ostendorff and Zheng Liu and Simon Clematide and Lester James Miranda and Alena Fenogenova and Guangyu Song and Ruqiya Bin Safi and Wen-Ding Li and Alessia Borghini and Federico Cassano and Hongjin Su and Jimmy Lin and Howard Yen and Lasse Hansen and Sara Hooker and Chenghao Xiao and Vaibhav Adlakha and Orion Weller and Siva Reddy and Niklas Muennighoff}, publisher = {arXiv}, journal={arXiv preprint arXiv:2502.13595}, year={2025}, url={https://arxiv.org/abs/2502.13595}, doi = {10.48550/arXiv.2502.13595}, } @article{muennighoff2022mteb, author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Lo{\"\i}c and Reimers, Nils}, title = {MTEB: Massive Text Embedding Benchmark}, publisher = {arXiv}, journal={arXiv preprint arXiv:2210.07316}, year = {2022} url = {https://arxiv.org/abs/2210.07316}, doi = {10.48550/ARXIV.2210.07316}, } ``` # Dataset Statistics <details> <summary> Dataset Statistics</summary> The following code contains the descriptive statistics from the task. These can also be obtained using: ```python import mteb task = mteb.get_task("CUADJointIPOwnershipLegalBenchClassification") desc_stats = task.metadata.descriptive_stats ``` ```json { "test": { "num_samples": 192, "number_of_characters": 71841, "number_texts_intersect_with_train": 0, "min_text_length": 68, "average_text_length": 374.171875, "max_text_length": 1415, "unique_text": 192, "unique_labels": 2, "labels": { "1": { "count": 96 }, "0": { "count": 96 } } }, "train": { "num_samples": 6, "number_of_characters": 4359, "number_texts_intersect_with_train": null, "min_text_length": 190, "average_text_length": 726.5, "max_text_length": 1761, "unique_text": 6, "unique_labels": 2, "labels": { "1": { "count": 3 }, "0": { "count": 3 } } } } ``` </details> --- This dataset card was automatically generated using [MTEB](https://github.com/embeddings-benchmark/mteb)
weepcat/summarization_partial_reward_model_random_length-1	weepcat	2025-01-21T10:40:04Z	17	0	[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-01-21T10:38:24Z	0	--- dataset_info: features: - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: prompt dtype: string splits: - name: train num_bytes: 1812682139.0 num_examples: 603820 - name: test num_bytes: 1629397885.0 num_examples: 543822 download_size: 735029273 dataset_size: 3442080024.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
robinsmits/ChatAlpaca-20K	robinsmits	2024-01-08T22:18:52Z	64	4	[ "task_categories:text-generation", "language:en", "license:apache-2.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us", "chat", "alpaca", "gpt-3.5" ]	[ "conversational", "text-generation" ]	2024-01-06T13:44:38Z	1	--- language: - en license: apache-2.0 size_categories: - 10K<n<100K task_categories: - conversational - text-generation pretty_name: ChatAlpaca 20K tags: - chat - alpaca - gpt-3.5 dataset_info: features: - name: id dtype: int32 - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: original num_bytes: 68350442 num_examples: 20000 - name: train num_bytes: 66983433.16 num_examples: 19600 - name: test num_bytes: 1367008.84 num_examples: 400 download_size: 69122205 dataset_size: 136700884.0 configs: - config_name: default data_files: - split: original path: data/original-* - split: train path: data/train-* - split: test path: data/test-* --- # Dataset Card for ChatAlpaca 20K ## ChatAlpaca: A Multi-Turn Dialogue Corpus based on Alpaca Instructions ### Dataset Description ChatAlpaca is a chat dataset that aims to help researchers develop models for instruction-following in multi-turn conversations. The dataset is an extension of the [Stanford Alpaca data](https://github.com/tatsu-lab/stanford_alpaca), which contains multi-turn instructions and their corresponding responses. ChatAlpaca is developed by Chinese Information Processing Laboratory at the Institute of Software, Chinese Academy of Sciences (www.icip.org.cn). In this dataset, we use ChatGPT (GPT-3.5-turbo) to generate follow-up utterances and continue the conversation with ChatGPT. This process results in multi-turn conversations where the simulated user provides instructions and ChatGPT responds accordingly. ### Dataset Structure The data in this repository consists of a JSON file chatalpaca-20k.json containing the multi-turn instruction-following conversations. Each item in the data file represents a different conversation between a simulated user and the ChatGPT. The data currently contains a total of 20,000 conversations. I've created 3 splits in the dataset: * original: all the data as available in the original chatalpaca-20k.json * train: 19600 rows for training * test: 400 rows for testing or validating. * The conversations in the dataset begin with an instruction, followed by a response from ChatGPT, which are from the Stanford Alpaca data. The conversation then continues with the user providing further instructions and ChatGPT responding accordingly. Each item in the dataset is a list of dictionaries, each dictionary contains the following fields: * id: int, identifier * messages: list, contains multiple dictionaries representing the conversations Each dictionary in the messages list contains the following fields: * role: str, with values "user" or "assistant"; * content: str, the conversation content. ! Note: In the original .json file the researchers used different field and variable names. I've renamed them to be consistent with the defacto standard as used for chat conversations. Here is an example of one conversation: ``` [ { "role": "user", "content": "Identify the odd one out: Twitter, Instagram, Telegram" }, { "role": "assistant", "content": "Telegram" }, { "role": "user", "content": "What makes Telegram different from Twitter and Instagram?" }, { "role": "assistant", "content": "Telegram is a cloud-based instant messaging app that focuses on privacy and security. Unlike Twitter and Instagram which are mainly used for following news, celebrities, and sharing images, Telegram was created as a secure messaging app for private and group communication. Telegram also offers more advanced features than Twitter and Instagram, such as the ability to schedule messages, create bots, and send encrypted messages." }, { "role": "user", "content": "Can you give me an example of how the scheduling messages feature can be useful on Telegram?" }, { "role": "assistant", "content": "Sure! The scheduling messages feature on Telegram can be useful in many different situations. Here's an example:\n\nLet's say you have a workgroup on Telegram, and you want to send a message to everyone in the group to remind them of a meeting. However, you know that most of the people in the group are busy at work during the time you want to send the message.\n\nThat's where the scheduling messages feature comes in. You can schedule the message to be sent at a later time when people are more likely to be free, such as during their lunch break or after work. This way, everyone in the group will receive the message at the same time, and you won't have to worry about anyone missing the important reminder.\n\nOverall, the scheduling messages feature can be really helpful for coordinating communication with groups of people on Telegram, whether it's for work, social events, or anything else." }, { "role": "user", "content": "Goodbye." } ] ``` ### Discussion of Biases As this dataset contains machine-generated texts it could contain potential biases. Verify and validate this for your specific usage scenario. ## Citation !! Note. I've only put this dataset on HuggingFace since it was not available. All credits go to the original researchers and creators. Please cite the original repository if you use the dataset. ``` @misc{ChatAlpaca, author = {Ning Bian and Hongyu Lin and Yaojie Lu and Xianpei Han and Le Sun and Ben He }, title = {ChatAlpaca: A Multi-Turn Dialogue Corpus based on Alpaca Instructions}, year = {2023}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/cascip/ChatAlpaca}}, } ```
sumuks/LaMP-AmazonProductReviews-4.25M	sumuks	2025-06-02T23:52:31Z	0	0	[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2024-07-26T16:02:34Z	0	--- dataset_info: features: - name: review_id dtype: string - name: review dtype: string - name: score dtype: string - name: profile_id dtype: string - name: total_profile_review_count dtype: int64 splits: - name: train num_bytes: 3397618326 num_examples: 4250311 download_size: 1908683064 dataset_size: 3397618326 configs: - config_name: default data_files: - split: train path: data/train-* ---
ToviTu/tebase-abstract-qa-grounded	ToviTu	2025-05-06T20:15:29Z	27	0	[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-05-01T18:06:20Z	0	--- dataset_info: features: - name: question dtype: string - name: answer dtype: string - name: abstract dtype: string - name: retrieved_contexts sequence: string - name: option_A dtype: string - name: option_B dtype: string - name: option_C dtype: string - name: option_D dtype: string splits: - name: train num_bytes: 46722 num_examples: 10 - name: test num_bytes: 5262289 num_examples: 990 download_size: 2806050 dataset_size: 5309011 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
JoveMiracle/cf_router_clean4k-6k	JoveMiracle	2025-03-28T20:31:38Z	17	0	[ "size_categories:1K<n<10K", "format:parquet", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-03-28T20:31:31Z	0	--- dataset_info: features: - name: embeddings sequence: float32 splits: - name: train num_bytes: 24585852 num_examples: 3999 download_size: 26925936 dataset_size: 24585852 configs: - config_name: default data_files: - split: train path: data/train-* ---
mteb/SNLHierarchicalClusteringP2P	mteb	2025-06-15T17:29:10Z	0	0	[ "task_categories:text-classification", "annotations_creators:derived", "multilinguality:monolingual", "language:nob", "license:cc-by-nc-4.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2502.13595", "arxiv:2210.07316", "region:us", "mteb", "text" ]	[ "text-classification" ]	2025-06-15T17:28:27Z	0	--- annotations_creators: - derived language: - nob license: cc-by-nc-4.0 multilinguality: monolingual task_categories: - text-classification task_ids: [] tags: - mteb - text dataset_info: features: - name: sentences dtype: string - name: labels sequence: string splits: - name: train num_bytes: 22764276 num_examples: 10874 - name: validation num_bytes: 1612730 num_examples: 819 - name: test num_bytes: 2747385 num_examples: 1300 download_size: 16642874 dataset_size: 27124391 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* --- <!-- adapted from https://github.com/huggingface/huggingface_hub/blob/v0.30.2/src/huggingface_hub/templates/datasetcard_template.md --> <div align="center" style="padding: 40px 20px; background-color: white; border-radius: 12px; box-shadow: 0 2px 10px rgba(0, 0, 0, 0.05); max-width: 600px; margin: 0 auto;"> <h1 style="font-size: 3.5rem; color: #1a1a1a; margin: 0 0 20px 0; letter-spacing: 2px; font-weight: 700;">SNLHierarchicalClusteringP2P</h1> <div style="font-size: 1.5rem; color: #4a4a4a; margin-bottom: 5px; font-weight: 300;">An <a href="https://github.com/embeddings-benchmark/mteb" style="color: #2c5282; font-weight: 600; text-decoration: none;" onmouseover="this.style.textDecoration='underline'" onmouseout="this.style.textDecoration='none'">MTEB</a> dataset</div> <div style="font-size: 0.9rem; color: #2c5282; margin-top: 10px;">Massive Text Embedding Benchmark</div> </div> Webscrabed articles from the Norwegian lexicon 'Det Store Norske Leksikon'. Uses articles categories as clusters. \| \| \| \|---------------\|---------------------------------------------\| \| Task category \| t2c \| \| Domains \| Encyclopaedic, Non-fiction, Written \| \| Reference \| https://huggingface.co/datasets/adrlau/navjordj-SNL_summarization_copy \| ## How to evaluate on this task You can evaluate an embedding model on this dataset using the following code: ```python import mteb task = mteb.get_task("SNLHierarchicalClusteringP2P") evaluator = mteb.MTEB([task]) model = mteb.get_model(YOUR_MODEL) evaluator.run(model) ``` <!-- Datasets want link to arxiv in readme to autolink dataset with paper --> To learn more about how to run models on `mteb` task check out the [GitHub repository](https://github.com/embeddings-benchmark/mteb). ## Citation If you use this dataset, please cite the dataset as well as [mteb](https://github.com/embeddings-benchmark/mteb), as this dataset likely includes additional processing as a part of the [MMTEB Contribution](https://github.com/embeddings-benchmark/mteb/tree/main/docs/mmteb). ```bibtex @mastersthesis{navjord2023beyond, author = {Navjord, J{\\o}rgen Johnsen and Korsvik, Jon-Mikkel Ryen}, school = {Norwegian University of Life Sciences, {\\AA}s}, title = {Beyond extractive: advancing abstractive automatic text summarization in Norwegian with transformers}, year = {2023}, } @article{enevoldsen2025mmtebmassivemultilingualtext, title={MMTEB: Massive Multilingual Text Embedding Benchmark}, author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Michail and John Yang and Manuel Faysse and Aleksei Vatolin and Nandan Thakur and Manan Dey and Dipam Vasani and Pranjal Chitale and Simone Tedeschi and Nguyen Tai and Artem Snegirev and Michael Günther and Mengzhou Xia and Weijia Shi and Xing Han Lù and Jordan Clive and Gayatri Krishnakumar and Anna Maksimova and Silvan Wehrli and Maria Tikhonova and Henil Panchal and Aleksandr Abramov and Malte Ostendorff and Zheng Liu and Simon Clematide and Lester James Miranda and Alena Fenogenova and Guangyu Song and Ruqiya Bin Safi and Wen-Ding Li and Alessia Borghini and Federico Cassano and Hongjin Su and Jimmy Lin and Howard Yen and Lasse Hansen and Sara Hooker and Chenghao Xiao and Vaibhav Adlakha and Orion Weller and Siva Reddy and Niklas Muennighoff}, publisher = {arXiv}, journal={arXiv preprint arXiv:2502.13595}, year={2025}, url={https://arxiv.org/abs/2502.13595}, doi = {10.48550/arXiv.2502.13595}, } @article{muennighoff2022mteb, author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Loïc and Reimers, Nils}, title = {MTEB: Massive Text Embedding Benchmark}, publisher = {arXiv}, journal={arXiv preprint arXiv:2210.07316}, year = {2022} url = {https://arxiv.org/abs/2210.07316}, doi = {10.48550/ARXIV.2210.07316}, } ``` # Dataset Statistics <details> <summary> Dataset Statistics</summary> The following code contains the descriptive statistics from the task. These can also be obtained using: ```python import mteb task = mteb.get_task("SNLHierarchicalClusteringP2P") desc_stats = task.metadata.descriptive_stats ``` ```json { "test": { "num_samples": 1300, "number_of_characters": 2583029, "min_text_length": 400, "average_text_length": 1986.9453846153847, "max_text_length": 68710, "unique_texts": 968, "min_labels_per_text": 1, "average_labels_per_text": 4.136153846153846, "max_labels_per_text": 201, "unique_labels": 1246, "labels": { "Realfag": { "count": 89 }, "Fysikk": { "count": 32 }, "Varme- og stoffl\u00e6re": { "count": 3 }, "Spr\u00e5k og litteratur": { "count": 139 }, "Spr\u00e5kvitenskapens fagdisipliner": { "count": 20 }, "Pragmatikk": { "count": 1 }, "Onomastikk": { "count": 14 }, "Personnavn": { "count": 14 }, "Fornavn": { "count": 14 }, "Guttenavn": { "count": 9 }, "Kunst og estetikk": { "count": 201 }, "Metall- og smykkekunst": { "count": 1 }, "Biologi": { "count": 92 }, "Vitenskapsgrener i biologien": { "count": 24 }, "Botanikk": { "count": 8 }, "Planteanatomi": { "count": 5 }, "Plantenes vevsystemer": { "count": 1 }, "Andre vev hos planter": { "count": 1 }, "Teknologi og industri": { "count": 97 }, "Transport": { "count": 35 }, "Navigasjon": { "count": 2 }, "Kjemi": { "count": 28 }, "Polymerkjemi": { "count": 3 }, "Sport og spill": { "count": 28 }, "Ballsport": { "count": 15 }, "Biljard": { "count": 2 }, "S\u00f8m": { "count": 8 }, " kl\u00e6r og mote": { "count": 8 }, "Sko": { "count": 1 }, "Veterin\u00e6rmedisin": { "count": 2 }, "Fiskehelse": { "count": 2 }, "Fotball": { "count": 9 }, "Norsk fotball": { "count": 4 }, "Musikk": { "count": 69 }, "Klassisk musikk": { "count": 25 }, "Den klassiske musikkens historie": { "count": 12 }, "Klassisk musikk f\u00f8r 1600": { "count": 1 }, "M\u00e5l og vekt": { "count": 7 }, "Eldre m\u00e5leenheter": { "count": 1 }, "Historie": { "count": 192 }, "Kulturhistorie": { "count": 6 }, "Folkelige skikker og tradisjoner": { "count": 2 }, "Spill": { "count": 3 }, "Brettspill": { "count": 2 }, "Biokjemi": { "count": 1 }, "Aminosyrer": { "count": 1 }, "Geografi": { "count": 178 }, "Norges geografi": { "count": 45 }, "Agder": { "count": 4 }, "Lindesnes": { "count": 1 }, "Verdens geografi": { "count": 128 }, "Afrika": { "count": 26 }, "Kapp Verdes geografi": { "count": 1 }, "Viken": { "count": 9 }, "Halden": { "count": 1 }, "Samfunn": { "count": 97 }, "Samfunnsfag": { "count": 26 }, "Statsvitenskap": { "count": 7 }, "Valgforskning og sammenliknende politikk": { "count": 1 }, "Politiske begreper": { "count": 1 }, "Planteriket": { "count": 24 }, "Dekkfr\u00f8ete planter": { "count": 24 }, "Enfr\u00f8bladete planter": { "count": 2 }, "Aspargesordenen": { "count": 1 }, "Orkid\u00e9familien": { "count": 1 }, "Marihandslekta": { "count": 1 }, "Jus": { "count": 34 }, "Formuerett": { "count": 8 }, "Selskapsrett": { "count": 5 }, "Telekommunikasjon og kringkasting": { "count": 2 }, "Kommunikasjonsteknologi": { "count": 2 }, "Oseania": { "count": 6 }, "Australias geografi": { "count": 2 }, "Jernbane og sporvei": { "count": 1 }, "Jernbanebiografier": { "count": 1 }, "Verdens historie og samtidshistorie": { "count": 126 }, "Europa": { "count": 192 }, "Den greske antikken": { "count": 6 }, "Sj\u00f8fart og skipsindustri": { "count": 16 }, "Fyrvesen og losvesen": { "count": 5 }, "Fyrvesen": { "count": 4 }, "Norske fyr": { "count": 4 }, "Norsk og nordisk historie": { "count": 26 }, "Norges historie": { "count": 20 }, "Norges historie fra 1945 til 1970": { "count": 1 }, "Nord- og Mellom-Amerika": { "count": 24 }, "Honduras\u2019 geografi": { "count": 1 }, "Historiske hjelpevitenskaper": { "count": 18 }, "Slektsforskning og genealogi": { "count": 17 }, "Utenlandske slekter": { "count": 7 }, "Folkegrupper i Nord- og Mellom-Amerika": { "count": 3 }, "Folkegrupper i Nord-Amerika": { "count": 3 }, "Litteratur i verden": { "count": 88 }, "Nord- og Mellom-Amerikas litteratur": { "count": 11 }, "USAs litteratur": { "count": 7 }, "USAs litteratur p\u00e5 1600 og 1700-tallet": { "count": 1 }, "Religion og filosofi": { "count": 95 }, "Religioner og livssyn": { "count": 61 }, "Kristendom": { "count": 48 }, "Det gamle testamentet": { "count": 2 }, "Personer i Det gamle testamentet": { "count": 2 }, "Tofr\u00f8bladete planter": { "count": 21 }, "Vierordenen": { "count": 3 }, "Vierfamilien": { "count": 1 }, "Vierslekta": { "count": 1 }, "Afrikas litteratur": { "count": 2 }, "Elfenbenskystens litteratur": { "count": 1 }, "N\u00e6ringsmidler og husholdning": { "count": 13 }, "Mat": { "count": 7 }, "Ulike lands kj\u00f8kken": { "count": 2 }, "S\u00f8r-Europas kj\u00f8kken": { "count": 1 }, "Italiensk mat": { "count": 1 }, "Klassisk musikk 1900\u20131950": { "count": 3 }, "Norske klassiske komponister og verker 1900\u20131950": { "count": 1 }, "Atferdsbiologi": { "count": 1 }, "Skip og skipstyper": { "count": 5 }, "Seilskip": { "count": 2 }, "Demografi": { "count": 2 }, "Filosofiens fagdisipliner": { "count": 12 }, "Filosofisk logikk": { "count": 1 }, "Historiske b\u00e5ttyper": { "count": 2 }, "Vikingskip": { "count": 1 }, "Bildende kunst": { "count": 49 }, "Kunstvitenskap": { "count": 5 }, "Termer og begreper i bildende kunst": { "count": 4 }, "Rubladordenen": { "count": 3 }, "Rubladfamilien": { "count": 3 }, "\u00c5kersteinfr\u00f8slekta": { "count": 1 }, "Familierett": { "count": 3 }, "Oslo": { "count": 1 }, "Atom- og kjernefysikk": { "count": 3 }, "Teknologi": { "count": 2 }, "Sjakk": { "count": 1 }, "Frankrikes historie": { "count": 11 }, "Frankrikes samtidshistorie": { "count": 3 }, "Italias geografi": { "count": 4 }, "Storbritannia og Nord-Irlands geografi": { "count": 13 }, "Katolisisme": { "count": 8 }, "Klostervesenet": { "count": 4 }, "Verdens historie": { "count": 5 }, "Den kalde krigen": { "count": 2 }, "Cellens organeller og mikrostruktur": { "count": 1 }, "Vekst og vekstanlegg": { "count": 1 }, "Analytisk kjemi": { "count": 2 }, "Spektroskopi": { "count": 2 }, "Grammatikk": { "count": 2 }, "Morfologi": { "count": 2 }, "Finlands litteratur": { "count": 4 }, "Utdanning og forskning": { "count": 12 }, "Pedagogikk": { "count": 3 }, "Biografier innen pedagogisk teori": { "count": 2 }, "Frankrikes litteratur": { "count": 14 }, "Frankrikes litteratur p\u00e5 1700-tallet": { "count": 2 }, "Psykologi": { "count": 4 }, "Personlighetspsykologi": { "count": 3 }, "Musikkbransje": { "count": 1 }, "Plateselskaper": { "count": 1 }, "Romanias historie": { "count": 3 }, "IT": { "count": 4 }, "Internett": { "count": 2 }, "Antigua og Barbudas geografi": { "count": 1 }, "Norges historie fra 1660 til 1814": { "count": 3 }, "Nordland": { "count": 6 }, "Bindal": { "count": 1 }, "Storbritannia og Nord-Irlands historie": { "count": 7 }, "Italias litteratur": { "count": 4 }, "Italias litteratur p\u00e5 1500-tallet": { "count": 2 }, "Arbeid og velferd": { "count": 4 }, "Arbeidsliv": { "count": 2 }, "Arbeidslivsorganisasjoner": { "count": 1 }, "Europas geografi generelt": { "count": 2 }, "Internasjonale dirigenter": { "count": 3 }, "Popul\u00e6rmusikk": { "count": 20 }, "Pop og rock": { "count": 11 }, "Internasjonal pop og rock": { "count": 10 }, "Afrikas historie": { "count": 2 }, "USAs historie": { "count": 5 }, "USAs historie fra 1960": { "count": 2 }, "Skipstyper": { "count": 1 }, "De ortodokse kirker": { "count": 2 }, "Sveriges litteratur": { "count": 5 }, "Sveriges litteratur 1900-1960": { "count": 2 }, "Avtalerett": { "count": 2 }, "Jentenavn": { "count": 5 }, "Energi": { "count": 6 }, "Belysning": { "count": 2 }, "Asia": { "count": 44 }, "Indias geografi": { "count": 3 }, "Br\u00f8nn\u00f8y": { "count": 1 }, "Anatomi": { "count": 3 }, "Insektenes anatomi og fysiologi": { "count": 1 }, "Pakistans geografi": { "count": 2 }, "Historiske religioner": { "count": 8 }, "Gresk religion": { "count": 2 }, "\u00d8konomi og n\u00e6ringsliv": { "count": 25 }, "N\u00e6ringsliv": { "count": 10 }, "Bedrifter og personer": { "count": 9 }, "Bedrifter i internasjonal n\u00e6ringslivshistorie": { "count": 2 }, "Politikk og offentlig forvaltning": { "count": 12 }, "Norsk politikk og offentlig forvaltning": { "count": 9 }, "Partier og politikere": { "count": 7 }, "Norske politikere": { "count": 7 }, "Tidligere politikere": { "count": 5 }, "Belarus\u2019 geografi": { "count": 1 }, "Matematikk": { "count": 6 }, "Sannsynlighet og statistikk": { "count": 2 }, "Statistikk": { "count": 2 }, "Film": { "count": 23 }, " TV og teater": { "count": 23 }, "Film og TV": { "count": 18 }, "Norske filmer og TV-serier": { "count": 1 }, "Arkitektur og landskap": { "count": 29 }, "Arkitekturhistorie": { "count": 9 }, "Islamsk arkitekturhistorie": { "count": 2 }, "Organisk kjemi": { "count": 7 }, "Organiske forbindelser": { "count": 7 }, "Historievitenskap": { "count": 8 }, "Historikere": { "count": 4 }, "Storbritannia og Nord-Irlands litteratur": { "count": 8 }, "Storbritannia og Nord-Irlands litteratur p\u00e5 1900-tallet": { "count": 3 }, "Folkegrupper i Afrika": { "count": 3 }, "Spr\u00e5kvitenskapens grunnbegreper": { "count": 1 }, "Luftfart": { "count": 6 }, "Luftfart\u00f8y": { "count": 1 }, "Sivilflytyper": { "count": 1 }, "Passasjerfly": { "count": 1 }, "Bygg og anlegg": { "count": 6 }, "Betong": { "count": 2 }, " sement og m\u00f8rtel": { "count": 2 }, "S\u00f8r-Amerikas geografi": { "count": 9 }, "Argentinas geografi": { "count": 2 }, "Bosnia-Hercegovinas geografi": { "count": 2 }, "Folkemusikk": { "count": 1 }, "Kristendommens historie": { "count": 6 }, "Tidlig kristendom": { "count": 4 }, "Den norske kirke": { "count": 5 }, "Buddhisme": { "count": 2 }, "Nyreligi\u00f8sitet": { "count": 2 }, "\u00d8stlig innflytelse": { "count": 1 }, "Medier": { "count": 17 }, "Forlagsdrift": { "count": 1 }, "Amt og len i Norge": { "count": 1 }, "Oster": { "count": 3 }, "Tekstiler": { "count": 4 }, "Flyteknikk": { "count": 1 }, "Flygeteori": { "count": 1 }, "Kirker": { "count": 7 }, " slott og g\u00e5rder": { "count": 7 }, "Slott og palasser": { "count": 3 }, "Klassisk musikk i barokken": { "count": 4 }, "Storbritannia og Nord-Irlands litteratur p\u00e5 1700-tallet": { "count": 3 }, "Drikke": { "count": 3 }, "Vin": { "count": 2 }, "Vinterminologi": { "count": 1 }, "Jazz": { "count": 17 }, "Nord-Amerikanske jazzut\u00f8vere og -ensembler": { "count": 10 }, " 1920 \u2013 1960": { "count": 2 }, "Danmarks geografi": { "count": 5 }, "Filippinenes geografi": { "count": 1 }, "Sj\u00f8merker": { "count": 1 }, "Elektrokjemi og metallurgi": { "count": 3 }, "Legeringer": { "count": 1 }, "St\u00e5l og andre jernlegeringer": { "count": 1 }, "Penger": { "count": 4 }, "Numismatikk": { "count": 2 }, "Taiwans geografi": { "count": 1 }, "Burkina Fasos geografi": { "count": 3 }, "Blues": { "count": 2 }, "Internasjonale bluesmusikere": { "count": 2 }, "Journalistikk": { "count": 2 }, "Journalistiske begreper": { "count": 2 }, "Middelalderens arkitekturhistorie": { "count": 4 }, "Frankrikes geografi": { "count": 8 }, "Jazzens historie": { "count": 1 }, "Tysk-romerske rike": { "count": 1 }, "Biografier i Det tysk-romerske riket": { "count": 1 }, "Geometri og topologi": { "count": 3 }, "Algebraisk geometri": { "count": 3 }, "USAs geografi": { "count": 7 }, "Delstater og omr\u00e5der i USA": { "count": 1 }, "Meteorologi": { "count": 2 }, "Klima": { "count": 1 }, "Klima i Norge": { "count": 1 }, "Norske tradisjonsb\u00e5ter": { "count": 1 }, "Nordnorske tradisjonsb\u00e5ter": { "count": 1 }, "Politi og kriminalitet": { "count": 4 }, "Politivesen": { "count": 2 }, "Politifaglige begreper": { "count": 2 }, "Kulturinstitusjoner": { "count": 6 }, "Museum": { "count": 3 }, "Filosofiens historie": { "count": 9 }, "Middelalderens og renessansens filosofi": { "count": 4 }, "Forsvar og sikkerhet": { "count": 18 }, "Forsvar i verden": { "count": 3 }, "Bokkunst og skrift": { "count": 2 }, "Skriftdesign og typografi": { "count": 1 }, "Typografer og skriftdesignere": { "count": 1 }, "Frankrikes nyere litteratur": { "count": 3 }, "Romerrikets litteratur": { "count": 2 }, "Verk i Romerrikets litteratur": { "count": 1 }, "Dyreriket": { "count": 30 }, "Ryggstrengdyr": { "count": 23 }, "Virveldyr": { "count": 26 }, "Fugler": { "count": 8 }, "Dykkere": { "count": 1 }, "Monarki": { "count": 1 }, "Maskiner": { "count": 10 }, "Maskinelementer": { "count": 1 }, "Jus generelt": { "count": 2 }, "Petroleum": { "count": 6 }, "Petroleumsutvinning": { "count": 4 }, "Boreteknologi": { "count": 1 }, "Landbruk": { "count": 8 }, "Husdyr": { "count": 7 }, "Hund": { "count": 5 }, "Hunderaser": { "count": 5 }, "Offentlig politikk og administrasjon": { "count": 3 }, "Politisk og \u00f8konomisk filosofi": { "count": 5 }, "Internasjonal tekstilindustri": { "count": 1 }, "Spanias geografi": { "count": 6 }, "Multippelenheter i SI-systemet": { "count": 1 }, " 1980 til i dag": { "count": 7 }, "Salmesang": { "count": 2 }, "Milit\u00e6re biografier": { "count": 4 }, "Norske milit\u00e6re biografier": { "count": 2 }, "Kristne trossamfunn": { "count": 9 }, "Spr\u00e5kforskere": { "count": 2 }, "Norske spr\u00e5kforskere og spr\u00e5kfolk": { "count": 1 }, "Romerrikets historie": { "count": 10 }, "Filmteknikk": { "count": 2 }, "Europeisk film og TV": { "count": 6 }, "Europeiske filmer og tv-serier": { "count": 1 }, "Bil": { "count": 8 }, "Bilfag": { "count": 4 }, "Bilens sikkerhetssystemer": { "count": 2 }, "Bygningstyper": { "count": 2 }, "Norges historie fra 1814 til 1884": { "count": 2 }, "Europeiske jazzut\u00f8vere og -ensembler": { "count": 2 }, " 1920 \u2013 1980": { "count": 4 }, "S\u00f8r-Amerika": { "count": 7 }, "Bolivias historie": { "count": 2 }, "Internasjonalt milit\u00e6rt samarbeid": { "count": 2 }, "Internasjonale milit\u00e6re organisasjoner": { "count": 2 }, "NATO": { "count": 2 }, "Kristen teologi og trosl\u00e6re": { "count": 2 }, "Leddyr": { "count": 4 }, "Insekter": { "count": 4 }, "Tovinger": { "count": 1 }, "Gallmygg": { "count": 1 }, "Dasineura": { "count": 1 }, "Mauritius\u2019 historie": { "count": 1 }, "Mauritius\u2019 samtidshistorie": { "count": 1 }, "Historiske riker i Sentral-Afrika": { "count": 1 }, "Politikkomr\u00e5der": { "count": 2 }, "Milj\u00f8vern": { "count": 1 }, "Milj\u00f8bevegelsen": { "count": 1 }, "Programmering": { "count": 1 }, "Polens historie": { "count": 1 }, "Fotografi": { "count": 2 }, "Fotohistoriske biografier": { "count": 1 }, "Skipstekniske og nautiske begrep": { "count": 5 }, "Immaterialrett": { "count": 1 }, "Opphavsrett": { "count": 1 }, "Kontormaskiner": { "count": 1 }, "Sosiologi": { "count": 6 }, "Sosiologer": { "count": 1 }, "Plantenes form": { "count": 3 }, "Fr\u00f8 og formeringsorganer": { "count": 1 }, "Genealoger": { "count": 1 }, "Storbritannias samtidshistorie": { "count": 1 }, "Samtidskunst": { "count": 10 }, "Skulptur og mosaikk i samtidskunsten": { "count": 4 }, "Bolig og eiendom": { "count": 3 }, "Volleyball": { "count": 1 }, "V\u00e6r": { "count": 1 }, "Skyer og nedb\u00f8r": { "count": 1 }, "Bangladesh' historie": { "count": 1 }, "Bangladesh' samtidshistorie": { "count": 1 }, "Spurvefugler": { "count": 2 }, "Kinas geografi": { "count": 1 }, "V\u00e5pen og milit\u00e6rt materiell": { "count": 3 }, "Marinefart\u00f8y": { "count": 1 }, "Undervannsb\u00e5ter": { "count": 1 }, "Belgias franskspr\u00e5klige litteratur": { "count": 4 }, "Motorkj\u00f8ret\u00f8yer": { "count": 1 }, "Israels historie": { "count": 1 }, "Astronomi": { "count": 17 }, "Solsystemet": { "count": 2 }, "Colombias geografi": { "count": 2 }, "Norges historie fra 1050 til 1300": { "count": 3 }, "\u00d8vrig vintersport": { "count": 2 }, "Skiskyting": { "count": 1 }, "Vestland": { "count": 8 }, "B\u00f8mlo": { "count": 1 }, "Moderne okkultisme": { "count": 1 }, "Frankrikes litteratur p\u00e5 1800-tallet": { "count": 3 }, "Antropologi": { "count": 6 }, "Antropologer": { "count": 3 }, "Musikkteori": { "count": 2 }, "Tonalitet": { "count": 1 }, "Internasjonale bedrifter og varemerker": { "count": 4 }, "Religionsvitenskap": { "count": 6 }, "Spr\u00e5ktypologi": { "count": 1 }, "Ungarns historie": { "count": 2 }, "Vade-": { "count": 2 }, " m\u00e5ke- og alkefugler": { "count": 2 }, "Oseanias litteratur": { "count": 3 }, "New Zealands litteratur": { "count": 1 }, "Pattedyr": { "count": 10 }, "Spissmusdyr": { "count": 1 }, "Spissmusfamilien": { "count": 1 }, "Soricinae": { "count": 1 }, "Soricini": { "count": 1 }, "Sorex": { "count": 1 }, "Fysikalsk kjemi": { "count": 1 }, "Litteraturvitenskap": { "count": 7 }, "Litteraturforskere og kritikere": { "count": 3 }, "Aserbajdsjans historie": { "count": 1 }, "Rettssosiologi": { "count": 1 }, "Chiles geografi": { "count": 1 }, "Norske bedrifter og varemerker": { "count": 3 }, "Klassisk musikk p\u00e5 1800-tallet": { "count": 4 }, "Internasjonale klassiske komponister og verker p\u00e5 1800-tallet": { "count": 3 }, "Flyindustri": { "count": 4 }, "Flyselskaper": { "count": 2 }, "Racketsport": { "count": 2 }, "Tennis": { "count": 2 }, "Prosessmetallurgi": { "count": 1 }, "Tysklands litteratur": { "count": 6 }, "Tysklands litteratur 1900-1950": { "count": 1 }, "Norske klassiske instrumentalister": { "count": 2 }, "Innlandet": { "count": 2 }, "Eidskog": { "count": 1 }, "Nord-amerikansk film og TV": { "count": 7 }, "Nord-amerikanske skuespillere": { "count": 5 }, "Internasjonal politikk": { "count": 2 }, "Troms og Finnmark": { "count": 3 }, "Bardu": { "count": 1 }, "Hinduisme": { "count": 3 }, "Aust-Agder": { "count": 1 }, "Kirkemusikk": { "count": 1 }, "Australias litteratur": { "count": 2 }, "Kunsthistorie": { "count": 31 }, "Ekspresjonisme og fauvisme": { "count": 1 }, "Vannforsyning": { "count": 1 }, "\u00d8vrige sporter": { "count": 2 }, "\u00d8vrig konkurranseidrett": { "count": 1 }, "Norsk pop og rock": { "count": 1 }, "Frankrikes litteratur p\u00e5 1600-tallet": { "count": 1 }, "Arkitekter og arkitektur-institusjoner": { "count": 10 }, "Internasjonale arkitekter fra 1600 til 1900": { "count": 2 }, "Dyrenes anatomi": { "count": 1 }, "Bangladesh' geografi": { "count": 3 }, "Benins historie": { "count": 1 }, "Benins samtidshistorie": { "count": 1 }, "Elektromagnetisme": { "count": 4 }, "Neo-ekspresjonisme og figurativ billedkunst etter 1945": { "count": 4 }, "N\u00e6ringsmiddelteknologi": { "count": 2 }, "Tr\u00f8ndelag": { "count": 3 }, "Skaun": { "count": 1 }, "Sigdal": { "count": 1 }, "Tysklands historie": { "count": 4 }, "Tysklands historie fra 1933 til 1945": { "count": 1 }, "Spr\u00e5kfilosofi": { "count": 1 }, "Kjerneenergi": { "count": 1 }, "Kjernekraftverk": { "count": 1 }, "Reiseliv": { "count": 3 }, "Bedrifter og organisasjoner i internasjonalt reiseliv": { "count": 2 }, "Norske dirigenter": { "count": 1 }, "Soppriket": { "count": 10 }, "Stilksporesopper": { "count": 9 }, "Hymeniesopper": { "count": 7 }, "Ekte hymeniesopper": { "count": 7 }, "Agaricomycetidae": { "count": 5 }, "Skivesoppordenen": { "count": 5 }, "Tricholomataceae": { "count": 1 }, "Ridderhatter": { "count": 1 }, "Indonesias geografi": { "count": 4 }, "Forskningsmetode": { "count": 5 }, "Frankrikes litteratur p\u00e5 1900-tallet": { "count": 4 }, "Aviser": { "count": 9 }, "Avisredakt\u00f8rer": { "count": 2 }, "Portugals litteratur": { "count": 1 }, "Utdanningshistorie": { "count": 1 }, "Pumper og turbiner": { "count": 3 }, "Byer i USA": { "count": 4 }, "USA-assosierte stater og territorer i Oseania": { "count": 1 }, "Korsblomstordenen": { "count": 3 }, "Korsblomstfamilien": { "count": 3 }, "Rublomslekta": { "count": 1 }, "Lyngordenen": { "count": 1 }, "Lyngfamilien": { "count": 1 }, "B\u00e6rlyngslekta": { "count": 1 }, " 1960 \u2013 1980": { "count": 1 }, "Geologi": { "count": 11 }, "Bergarter": { "count": 3 }, "Metamorfe bergarter": { "count": 1 }, "Nederlandsk og flamsk billedkunst 1400-1750": { "count": 2 }, "Kristen misjonsvirksomhet": { "count": 6 }, "Benins geografi": { "count": 1 }, "Romanias geografi": { "count": 2 }, "Molekyl\u00e6rbiologi": { "count": 1 }, "Metoder i celle- og molekyl\u00e6rbiologien": { "count": 1 }, "Skrinneblomslekta": { "count": 1 }, "Norsk bildende kunst fra 1800-1945": { "count": 3 }, "Englands historie": { "count": 1 }, "Kinas historie": { "count": 1 }, "Republikken Kinas historie (1912\u20131949)": { "count": 1 }, "Bunad": { "count": 1 }, " kofter og folkedrakt": { "count": 1 }, "Islam": { "count": 3 }, "Retninger i islam": { "count": 3 }, "Postimpresjonisme": { "count": 2 }, " symbolisme og art nouveau": { "count": 2 }, "Dyrevern": { "count": 1 }, "Tidsregning": { "count": 2 }, "Temabasert reiseliv": { "count": 1 }, "Turisthytter": { "count": 1 }, "Geomorfologi": { "count": 1 }, "M\u00f8re og Romsdal": { "count": 3 }, "Fjord": { "count": 1 }, "Formering": { "count": 1 }, "Design": { "count": 4 }, "M\u00f8bler og interi\u00f8rtyper": { "count": 1 }, "Ordforklaringer": { "count": 10 }, "Uttrykk og ordtak": { "count": 3 }, "Petroleumsfelter": { "count": 2 }, "Brasils historie": { "count": 2 }, "Brasils samtidshistorie": { "count": 2 }, "Kildeskrifter": { "count": 3 }, "Norske slekter": { "count": 9 }, "Kamp- og kontaktsport": { "count": 2 }, "Asiatiske kampsporter": { "count": 1 }, "Stormfugler": { "count": 1 }, "Stormfuglfamilien": { "count": 1 }, "Thalassoica": { "count": 1 }, "Danmarks historie": { "count": 4 }, "Danmarks samtidshistorie": { "count": 1 }, "Personer innen astronomi": { "count": 3 }, "Romvirksomhet": { "count": 4 }, "Personer": { "count": 1 }, " bedrifter og organisasjoner innen romvirksomhet": { "count": 1 }, "Prefikser og suffikser": { "count": 1 }, "Kraftselskaper og kraftverk": { "count": 2 }, "Arkivfag": { "count": 2 }, "Vestfold og Telemark": { "count": 2 }, "Midt-Telemark": { "count": 1 }, "B\u00f8": { "count": 2 }, "Russlands geografi": { "count": 1 }, "Teknologi- og industrihistorie": { "count": 4 }, "Norsk teknologi- og industrihistorie": { "count": 4 }, "Bergverkshistorie": { "count": 1 }, "Statsvitere og institusjoner": { "count": 1 }, "Verdensmusikk": { "count": 2 }, "Country og bluegrass": { "count": 1 }, "Amerikanske country- og bluegrassartister": { "count": 1 }, "Barnehage": { "count": 2 }, "Internasjonale klassiske ensembler": { "count": 1 }, "Antikkens filosofi": { "count": 2 }, "Leppeblomstordenen": { "count": 3 }, "Kjempefamilien": { "count": 1 }, "Kjempeslekta": { "count": 1 }, "Industri": { "count": 4 }, "Metallarbeid": { "count": 2 }, "Geologer": { "count": 2 }, "Canadas historie": { "count": 1 }, "Canadas samtidshistorie": { "count": 1 }, "Sosiologisk teori": { "count": 4 }, "Palestinas historie": { "count": 2 }, "Palestinas samtidshistorie": { "count": 2 }, "Canadas franskspr\u00e5klige litteratur": { "count": 1 }, "Internasjonale tegnekunstnere": { "count": 2 }, "\u00d8sterrikes litteratur": { "count": 2 }, "\u00d8sterrikes litteratur f\u00f8r 1700-tallet": { "count": 1 }, "Str\u00e5lefinnefisker": { "count": 2 }, "Karpefisker": { "count": 1 }, "Karpefamilien": { "count": 1 }, "Rhodeus": { "count": 1 }, "Indonesias historie": { "count": 1 }, "Indonesias samtidshistorie": { "count": 1 }, "Samfunnssikkerhet og beredskap": { "count": 1 }, "Beredskap og kriseh\u00e5ndtering": { "count": 1 }, "Designteori og -historie": { "count": 1 }, "Grunnstoffer": { "count": 5 }, "Nyklassisisme og romantikk i bildende kunst": { "count": 1 }, "Rot hos planter": { "count": 1 }, "Kroatias litteratur": { "count": 1 }, "Flaggermus": { "count": 1 }, "Glattnesefamilien": { "count": 1 }, "Vespertilioninae": { "count": 1 }, "Plecotini": { "count": 1 }, "Barbastella": { "count": 1 }, "J\u00f8dedom": { "count": 2 }, "Tsjekkias geografi": { "count": 1 }, "Danmarks litteratur": { "count": 5 }, "Danmarks litteratur p\u00e5 1900-tallet": { "count": 4 }, "Fransk politikk": { "count": 1 }, "IT-historie": { "count": 1 }, "Personer i IT-historie": { "count": 1 }, "USAs litteratur 1900-1950": { "count": 1 }, "Internasjonal rett": { "count": 3 }, "Alminnelig folkerett": { "count": 3 }, "Lydteknologi": { "count": 1 }, "Flatormer": { "count": 1 }, "Bendelormer": { "count": 1 }, "Pseudophyllidea": { "count": 1 }, "Diphyllobothriidae": { "count": 1 }, "Asias litteratur": { "count": 3 }, "Irans litteratur": { "count": 1 }, "Realisme og impresjonisme": { "count": 5 }, "Kjernekjemi": { "count": 1 }, "Hellas\u2019 historie": { "count": 1 }, "Norske aviser": { "count": 2 }, "Ord og uttrykk p\u00e5 andre spr\u00e5k": { "count": 3 }, "Tyske ord og uttrykk": { "count": 2 }, "Storbritannia og Nord-Irlands litteratur p\u00e5 1600-tallet": { "count": 1 }, "Haier og skater": { "count": 1 }, "H\u00e5branner": { "count": 1 }, "Brugdefamilien": { "count": 1 }, "Cetorhinus": { "count": 1 }, "Rettskildel\u00e6re": { "count": 1 }, "Belgias historie": { "count": 1 }, "Usbekistans geografi": { "count": 1 }, "Elektronikk": { "count": 6 }, "Fjernsynsteknikk": { "count": 1 }, "Frankrikes litteratur f\u00f8r 1500-tallet": { "count": 1 }, "Begreper i botanikken": { "count": 2 }, "Costa Ricas litteratur": { "count": 1 }, "Macrocystidiaceae": { "count": 1 }, "Macrocystidia": { "count": 1 }, "Flagg og nasjonalsymboler": { "count": 2 }, "Flagg og v\u00e5pen": { "count": 2 }, "Milit\u00e6r teori": { "count": 1 }, "Arendal": { "count": 1 }, "Austrheim": { "count": 1 }, "Cubas historie": { "count": 1 }, "Cubas samtidshistorie": { "count": 1 }, "Motiver i bildende kunst": { "count": 1 }, "Strophariaceae": { "count": 1 }, "Skulptur og mosaikk i nyere tid": { "count": 3 }, "Europas \u00f8vrige historie": { "count": 3 }, "Europa p\u00e5 1900-tallet": { "count": 1 }, "Kjemiens historie": { "count": 1 }, "S\u00f8tvierordenen": { "count": 3 }, "S\u00f8tvierfamilien": { "count": 3 }, "S\u00f8tvierslekta": { "count": 2 }, "Andre verdenskrig": { "count": 2 }, "Tysklands litteratur p\u00e5 1800-tallet": { "count": 3 }, "Norske klassiske ensembler": { "count": 1 }, "Drammen": { "count": 1 }, "Perus geografi": { "count": 2 }, "Romobservatorier": { "count": 2 }, "Fagbegreper i antropologi": { "count": 3 }, "Botswanas historie": { "count": 1 }, "Botswanas samtidshistorie": { "count": 1 }, "Vortemelkfamilien": { "count": 2 }, "Fly- og helikopterprodusenter": { "count": 2 }, "Heraldikk": { "count": 1 }, "Grafikk": { "count": 1 }, "Genetikk": { "count": 2 }, "Bemannet romfart": { "count": 1 }, "Tyrkias geografi": { "count": 2 }, "Den katolske kirke": { "count": 1 }, "Erkebiskoper": { "count": 1 }, "Biografier i norsk teknologi- og industrihistorie": { "count": 2 }, "Vepser": { "count": 3 }, "Arverett og skifterett": { "count": 1 }, "\u00d8rland": { "count": 1 }, "Engelsk fotball": { "count": 2 }, "Engelske fotballspillere": { "count": 1 }, "Bibliotek": { "count": 1 }, "S\u00f8r-Amerikas litteratur": { "count": 2 }, "Colombias litteratur": { "count": 1 }, "Protestantisme": { "count": 4 }, "Samferdsel": { "count": 2 }, "Broer": { "count": 1 }, "Broer i Norge": { "count": 1 }, "Stilkvepser": { "count": 1 }, "Broddvepser": { "count": 1 }, "Apoidea": { "count": 1 }, "Grafisk industri": { "count": 3 }, "Teknologi og materialer i grafisk industri": { "count": 2 }, "Norske skuespillere": { "count": 4 }, "Aviser i Vestland": { "count": 1 }, "Magnoliids": { "count": 1 }, "Magnoliaordenen": { "count": 1 }, "Annonaceae": { "count": 1 }, "Den franske revolusjon": { "count": 1 }, "Teater": { "count": 1 }, "Internasjonale teaterinstitusjoner": { "count": 1 }, "Arkeologi": { "count": 9 }, "Nordisk arkeologi": { "count": 2 }, "Hvaler": { "count": 1 }, "Bardehvaler": { "count": 1 }, "Finnhvalfamilien": { "count": 1 }, "Balaenoptera": { "count": 1 }, "Folketro": { "count": 2 }, "Russland og Sovjetunionens historie": { "count": 5 }, "Russlands eldre historie": { "count": 3 }, "Blad": { "count": 1 }, "Europeiske filmskuespillere": { "count": 4 }, "Internasjonale klassiske komponister og verker i barokken": { "count": 2 }, "Samfunns\u00f8konomi": { "count": 1 }, "\u00d8konomisk politikk": { "count": 1 }, "Motorsport": { "count": 1 }, "Bilsport": { "count": 1 }, "Perus historie": { "count": 1 }, "Skipstekniske begrep": { "count": 2 }, "Glass og keramikk": { "count": 1 }, "Glass og keramikk \u2013 ut\u00f8vere": { "count": 1 }, "Brunrotfamilien": { "count": 1 }, "Bokkunst": { "count": 1 }, "Internasjonale klassiske instrumentalister": { "count": 1 }, "Dagblomordenen": { "count": 1 }, "Dagblomfamilien": { "count": 1 }, "Roseordenen": { "count": 1 }, "Rosefamilien": { "count": 1 }, "Epleslekta": { "count": 1 }, "USAs litteratur 1950-2000": { "count": 3 }, "Plantevepser": { "count": 1 }, "Tenthredinoidea": { "count": 1 }, "Bladvepser": { "count": 1 }, "Blennocampinae": { "count": 1 }, "Tomostethus": { "count": 1 }, "Franske s\u00f8rterritorier": { "count": 1 }, "Musikkinstrumenter": { "count": 1 }, "Elektriske musikkinstrumenter": { "count": 1 }, "Arbeidsrett": { "count": 1 }, "Optikk": { "count": 3 }, "Animasjonsfilm": { "count": 1 }, "Snipefamilien": { "count": 1 }, "Rogaland": { "count": 3 }, "Eigersund": { "count": 2 }, "Albanias historie": { "count": 2 }, "Sirenia": { "count": 1 }, "Dugongidae": { "count": 1 }, "Dugong": { "count": 1 }, "Dans": { "count": 5 }, "Scenisk dans": { "count": 2 }, "Moderne- og samtidsdans": { "count": 1 }, "Moderne- og samtidsdans: norske kunstnere og kompanier": { "count": 1 }, "Raketter": { "count": 2 }, "Obligasjonsrett": { "count": 4 }, "Myanmars historie": { "count": 1 }, "Myanmars samtidshistorie": { "count": 1 }, "Biografier i Romerrikets historie": { "count": 3 }, "Kantarellordenen": { "count": 1 }, "Clavulinaceae": { "count": 1 }, "Ringerike": { "count": 1 }, "Litteraturtyper": { "count": 7 }, "Barne- og ungdomslitteratur": { "count": 3 }, "Internasjonal barne- og ungdomslitteratur": { "count": 2 }, "Russland og Sovjetunionens litteratur": { "count": 1 }, "Russiske litteraturforskere og kritikere": { "count": 1 }, "Filippinenes historie": { "count": 1 }, "Filippinenes samtidshistorie": { "count": 1 }, "Norske jazzut\u00f8vere og -ensembler": { "count": 2 }, "Bedrifts\u00f8konomi": { "count": 5 }, "Norske tegnekunstnere": { "count": 2 }, "Argentinas litteratur": { "count": 1 }, "Islands geografi": { "count": 1 }, "Gnagere": { "count": 2 }, "Sciuromorpha": { "count": 1 }, "Ekornfamilien": { "count": 1 }, "Myosciurus": { "count": 1 }, "Paleontologi": { "count": 5 }, "Tokke": { "count": 1 }, "Soul og R&B": { "count": 1 }, "Internasjonal soul og R&B": { "count": 1 }, "Utenlandske spr\u00e5kforskere": { "count": 1 }, "Forglemmegeislekta": { "count": 2 }, "Slimriket": { "count": 1 }, "Strafferett": { "count": 1 }, "Mineraler": { "count": 4 }, "Silikatmineraler": { "count": 3 }, "Norges forsvar": { "count": 2 }, "Norske festninger og milit\u00e6ranlegg": { "count": 1 }, "Katolske ritualer og symboler": { "count": 2 }, "Irlands geografi": { "count": 1 }, "Jurister": { "count": 2 }, "Ulike lands musikk og musikktradisjoner": { "count": 1 }, "Albanias samtidshistorie": { "count": 1 }, "Varehandel": { "count": 1 }, "Psykologiens historie": { "count": 1 }, "Utenlandske aviser": { "count": 2 }, "Verdenshavene": { "count": 3 }, "Dyphavsgroper": { "count": 1 }, "Ulike lands arkitekturhistorie": { "count": 1 }, "Islands litteratur": { "count": 4 }, "Ulike lands kunst og kunsttradisjoner": { "count": 1 }, "Konstruksjonsteknikk": { "count": 1 }, "Canadas geografi": { "count": 1 }, "Bakterier": { "count": 1 }, "H\u00e5ndverk": { "count": 1 }, "Redskaper og festemidler": { "count": 1 }, "Utforsking av solsystemet": { "count": 1 }, "Vin i Europa": { "count": 1 }, "Vin i Frankrike": { "count": 1 }, "Myndigheter i Norge": { "count": 2 }, "Embets- og tjenestepersoner": { "count": 1 }, "Det 19. \u00e5rhundres filosofi": { "count": 1 }, "Nederlands historie": { "count": 1 }, "Norges historie fram til 1050": { "count": 1 }, "Barnevern": { "count": 1 }, "Rovpattedyr": { "count": 2 }, "Caniformia": { "count": 2 }, "Bj\u00f8rnefamilien": { "count": 1 }, "Tremarctos": { "count": 1 }, "Kirgisistans historie": { "count": 1 }, "Kirgisistans samtidshistorie": { "count": 1 }, "Krypdyr": { "count": 1 }, "Dinosaurer": { "count": 1 }, "\u00d8vrig europeisk malerkunst 1400-1750": { "count": 2 }, "Mesopotamia": { "count": 2 }, "Storg\u00e5rder og herreg\u00e5rder": { "count": 2 }, "Norske storg\u00e5rder": { "count": 2 }, "Internasjonale arkitekter og arkitektkontorer fra 1900 til i dag": { "count": 4 }, "Skriftspr\u00e5k": { "count": 1 }, "Alfabeter og skriftsystemer": { "count": 1 }, "Skrifttegn": { "count": 1 }, "Latinske bokstaver": { "count": 1 }, "Diakritiske tegn": { "count": 1 }, "Det 17. og 18. \u00e5rhundres filosofi": { "count": 2 }, "Norske arkitekter og arkitektkontorer fra 1900 til i dag": { "count": 3 }, "Asias kj\u00f8kken": { "count": 1 }, "Avisjournalister": { "count": 1 }, "V\u00e5pen": { "count": 2 }, "Artilleri": { "count": 1 }, "TV og radio": { "count": 1 }, "TV- og radiopersoner": { "count": 1 }, "Uorganisk kjemi": { "count": 3 }, "Myomorpha": { "count": 1 }, "Muroidea": { "count": 1 }, "Hamsterfamilien": { "count": 1 }, "Arvicolinae": { "count": 1 }, "Lemmini": { "count": 1 }, "Lemmus": { "count": 1 }, "Bilens drivlinje": { "count": 1 }, "Britisk Indiahav": { "count": 1 }, "Nyrealisme": { "count": 1 }, " nysaklighet og tendenskunst": { "count": 1 }, "Cellebiologi": { "count": 1 }, "Cellestrukturer": { "count": 1 }, "Tysklands geografi": { "count": 3 }, "Armenias geografi": { "count": 1 }, "Elektronisk navigasjon": { "count": 1 }, "Kinematografi": { "count": 1 }, "Spr\u00e5kfamilier": { "count": 3 }, "Indoeuropeiske spr\u00e5k": { "count": 3 }, "Romansk": { "count": 2 }, "Latin": { "count": 2 }, "Latinske verk": { "count": 2 }, "Folkegrupper i Asia": { "count": 1 }, "Folkegrupper i Sentral-Asia": { "count": 1 }, "Bilmerker": { "count": 2 }, "Eritreas geografi": { "count": 1 }, "Norr\u00f8n litteratur": { "count": 2 }, "Algebra": { "count": 1 }, "Kommutative algebraer og ringer": { "count": 1 }, "Israels geografi": { "count": 1 }, "Nellikordenen": { "count": 1 }, "Slireknefamilien": { "count": 1 }, "Syreslekta": { "count": 1 }, "And\u00f8y": { "count": 1 }, "Gulen": { "count": 1 }, "Rettshistorie": { "count": 2 }, "Kvinnherad": { "count": 1 }, "Bilhistoriske biografier": { "count": 1 }, "Jordans historie": { "count": 1 }, "Friidrett": { "count": 1 }, "L\u00f8p": { "count": 1 }, "Europeiske filmskapere": { "count": 1 }, "Oseania generelt": { "count": 1 }, "Industridesign": { "count": 1 }, "Fast eiendom": { "count": 1 }, "Milit\u00e6rvesen": { "count": 2 }, "Bank og finans": { "count": 2 }, "B\u00f8rs og finans": { "count": 2 }, "Internasjonale klassiske sangere": { "count": 2 }, "Nattravn- og seilerfugler": { "count": 1 }, "Seilerfamilien": { "count": 1 }, "Tachymarptis": { "count": 1 }, "Zoologi": { "count": 1 }, "Pedagogisk teori": { "count": 1 }, "Midt\u00f8sten": { "count": 4 }, "Midt\u00f8stens gamle kulturer": { "count": 4 }, "Oppdagelsesreiser": { "count": 3 }, "Urstilksporesopper": { "count": 1 }, "Ekte rustsopper": { "count": 1 }, "Rustsoppordenen": { "count": 1 }, "Pucciniaceae": { "count": 1 }, "Slektskap": { "count": 1 }, " familie og ekteskap": { "count": 1 }, "Akershus": { "count": 1 }, "Sk\u00f8ytesport": { "count": 1 }, "Eldre mynter og pengeenheter": { "count": 2 }, "Elektronisk musikk": { "count": 1 }, "Kunstinstitusjoner": { "count": 1 }, "Internasjonale kunstinstitusjoner": { "count": 1 }, "Norges historie fra 1884 til 1940": { "count": 5 }, "Plantefysiologi": { "count": 1 }, "Serbias historie": { "count": 1 }, "Ulike lands dansehistorie": { "count": 1 }, "Spanias litteratur": { "count": 1 }, "Spanias litteratur p\u00e5 1900-tallet": { "count": 1 }, "Israels litteratur": { "count": 1 }, "Skytesport": { "count": 1 }, "Viltm\u00e5l": { "count": 1 }, "H\u00e6r og landforsvar": { "count": 1 }, "Norsk og samisk litteratur": { "count": 11 }, "Nyere norsk litteratur": { "count": 5 }, "Italienske ord og uttrykk": { "count": 1 }, "USAs nyere litteratur": { "count": 2 }, "Nyklassisisme og historisme i arkitekturhistorien": { "count": 2 }, "Hygrophoraceae": { "count": 1 }, "Cuphophyllus": { "count": 1 }, "Ustabile grunnstoffer": { "count": 3 }, "Kubisme og futurisme": { "count": 1 }, "Krim": { "count": 1 }, "Krim i Norge": { "count": 1 }, "Namibias historie": { "count": 1 }, "Skifer": { "count": 1 }, "Rytme og tempo": { "count": 1 }, "Bl\u00f8tdyr": { "count": 2 }, "Snegler": { "count": 1 }, "Albuesnegler": { "count": 1 }, "Patelloidea": { "count": 1 }, "Patellidae": { "count": 1 }, "Patella": { "count": 1 }, "Angolas historie": { "count": 1 }, "Angolas samtidshistorie": { "count": 1 }, "Grunnoppl\u00e6ring": { "count": 2 }, "Yrkesfaglig utdanning": { "count": 2 }, "Bygg- og anleggsteknikk": { "count": 1 }, "Sveriges geografi": { "count": 3 }, "Andefugler": { "count": 1 }, "Andefamilien": { "count": 1 }, "Somateria": { "count": 1 }, "Rugby og amerikansk fotball": { "count": 1 }, "Broddsoppordenen": { "count": 1 }, "Hymenochaetaceae": { "count": 1 }, "Jordbruk": { "count": 1 }, "Trelast og treforedling": { "count": 2 }, "Papirindustri": { "count": 1 }, "Venezuelas geografi": { "count": 1 }, "Mystikere": { "count": 1 }, "Prosess": { "count": 1 }, "Straffeprosess": { "count": 1 }, "Institusjoner i klassisk musikk": { "count": 1 }, "Aviseiere og direkt\u00f8rer": { "count": 2 }, "Nord-amerikanske filmskapere": { "count": 2 }, "Norske kirkebygg": { "count": 2 }, "Utdanning i verden": { "count": 2 }, "Utdanning i Europa": { "count": 1 }, "Marokkos geografi": { "count": 1 }, "Trolldomsprosesser": { "count": 1 }, "Etiopias geografi": { "count": 1 }, "Petroleumshistorie": { "count": 1 }, "Ulykker i petroleumsbransjen": { "count": 1 }, "Anvendt elektromagnetisme": { "count": 1 }, "Tyrkiskspr\u00e5klig litteratur": { "count": 1 }, "Tyrkias litteratur": { "count": 1 }, "Indre \u00d8stfold": { "count": 1 }, "Eidsberg": { "count": 1 }, "Grafisk industrihistorie": { "count": 1 }, "Tingvoll": { "count": 1 }, "\u00d8kologi": { "count": 1 }, "Utviklingsbiologi": { "count": 1 }, "Fiskeri og havbruk": { "count": 1 }, "Norske fiskerier": { "count": 1 }, "Fiskeredskaper og fart\u00f8y": { "count": 1 }, "Bulgarias geografi": { "count": 2 }, "Nyere norsk sakprosa": { "count": 1 }, "Tremellomycetes": { "count": 1 }, "Tremellales": { "count": 1 }, "Tremellaceae": { "count": 1 }, "Cryptococcus": { "count": 1 }, "Norges litteratur 1800-tallet": { "count": 1 }, "Forskning og h\u00f8yere utdanning": { "count": 2 }, "Forskningsinstitutter": { "count": 1 }, "Transportrett": { "count": 2 }, "Sj\u00f8rett": { "count": 2 }, "Italias historie": { "count": 2 }, "Italias samtidshistorie": { "count": 1 }, "Internasjonale milit\u00e6re biografier": { "count": 2 }, "Portugisisk fotball": { "count": 1 }, "Medisin": { "count": 3 }, "Helse og samfunn": { "count": 2 }, "Medisinsk historie": { "count": 2 }, "Algeries geografi": { "count": 1 }, "Sveits\u2019 geografi": { "count": 2 }, "Klovdyr": { "count": 1 }, "Kvegfamilien": { "count": 1 }, "Bos": { "count": 1 }, "Norges litteratur 1900-1960": { "count": 1 }, "Mel\u00f8y": { "count": 1 }, "Religionsfilosofi": { "count": 1 }, "Sveits\u2019 litteratur": { "count": 2 }, "Sveits\u2019 franskspr\u00e5klige litteratur": { "count": 1 }, "Materialfysikk": { "count": 1 }, "Systematikk i biologien": { "count": 1 }, "Terrorisme": { "count": 1 }, "Norsk barne- og ungdomslitteratur f\u00f8r 2000": { "count": 1 }, "Krystallografi": { "count": 1 }, "Litter\u00e6re perioder og stiler": { "count": 1 }, "Ungarns litteratur": { "count": 1 }, "Semantikk": { "count": 1 }, "Norsk samtidskunst": { "count": 2 }, "Enebakk": { "count": 1 }, "Europeisk arkeologi": { "count": 1 }, "Tidlig abstrakt billedkunst": { "count": 1 }, "Cortinariaceae": { "count": 1 }, "Sl\u00f8rsopper": { "count": 1 }, "Sentralafrikanske republikks historie": { "count": 1 }, "Nord-Makedonias historie": { "count": 1 }, "Nord-Makedonias samtidshistorie": { "count": 1 }, "Ford\u00f8yelsessystemet": { "count": 1 }, "Ern\u00e6ring": { "count": 1 }, "Sveits\u2019 historie": { "count": 1 }, "Sveits\u2019 samtidshistorie": { "count": 1 }, "Grader og titler": { "count": 1 }, "Akademiske titler": { "count": 1 }, "New Zealands geografi": { "count": 1 }, "Sveriges historie": { "count": 1 }, "Sveriges kongehus": { "count": 1 }, "Norges historie fra 1940 til 1945": { "count": 2 }, "Klassisk religion": { "count": 1 }, "Astronomisk teknologi": { "count": 1 }, "Spanias historie": { "count": 1 }, "Spanias samtidshistorie": { "count": 1 }, "Sjangerl\u00e6re": { "count": 2 }, "epikk": { "count": 1 }, "Eidfjord": { "count": 1 }, "Orientering": { "count": 1 }, "Skotsk fotball": { "count": 1 }, "Leppeblomstfamilien": { "count": 1 }, "D\u00e5slekta": { "count": 1 }, "Estetikk": { "count": 2 }, "Nigerias historie": { "count": 1 }, "Nigerias samtidshistorie": { "count": 1 }, "Musikaler": { "count": 2 }, "Angolas geografi": { "count": 1 }, "Kristne ritualer og symboler": { "count": 2 }, "Radioteknikk": { "count": 1 }, "Internasjonale fotografer og fotokunstnere": { "count": 1 }, "Internasjonale klassiske komponister og verker 1900\u20131950": { "count": 2 }, "Norsk bildende kunst fra 1945 til 1990": { "count": 2 }, "Serbia og det gamle Jugoslavias litteratur": { "count": 1 }, "Polare ekspedisjoner og oppdagere": { "count": 1 }, "Italiensk fotball": { "count": 1 }, "Petroleumsselskaper": { "count": 1 }, "Datoartikler": { "count": 3 }, "Tysklands litteratur 1950-2000": { "count": 1 }, "M\u00e5ltider": { "count": 1 }, "Iraks historie": { "count": 1 }, "Iraks samtidshistorie": { "count": 1 }, "Irans historie": { "count": 1 }, "Irans samtidshistorie": { "count": 1 }, "Bod\u00f8": { "count": 1 }, "Nordiske jazzut\u00f8vere og -ensembler": { "count": 2 }, " 1980 til idag": { "count": 2 }, "Trelast- og treforedlingsindustri \u2013 historie": { "count": 1 }, "Det gamle Egypt": { "count": 1 }, "Norske ord og uttrykk": { "count": 1 }, "Papua Ny-Guineas geografi": { "count": 1 }, "Asker": { "count": 1 }, "Amfibier": { "count": 2 }, "Springpadder": { "count": 1 }, "Eleutherodactylidae": { "count": 1 }, "Eleutherodactylus": { "count": 1 }, "Tunneler": { "count": 1 }, "Tunneler i Norge": { "count": 1 }, "Salamandere": { "count": 1 }, "Plethodontidae": { "count": 1 }, "Aneides": { "count": 1 }, "H\u00e6ren": { "count": 1 }, "Kardeborreordenen": { "count": 1 }, "Kaprifolfamilien": { "count": 1 }, "Bl\u00e5knappslekta": { "count": 1 }, "Italias litteratur p\u00e5 1700-tallet": { "count": 1 }, "Skipsbygging": { "count": 1 }, "Skipskonstrukt\u00f8rer": { "count": 1 }, "Piggepleslekta": { "count": 1 }, "Sediment\u00e6re bergarter": { "count": 1 }, "Samfunnstyper": { "count": 1 }, "Boksing": { "count": 1 }, "Designinstitusjoner": { "count": 1 }, "De forente arabiske emiraters historie": { "count": 1 }, "De forente arabiske emiraters samtidshistorie": { "count": 1 }, "Folketrygd og pensjon": { "count": 1 }, "Forbrukerelektronikk": { "count": 1 }, "Utdanning i S\u00f8r-Amerika": { "count": 1 }, "Asias geografi generelt": { "count": 1 }, "Urverk og klokker": { "count": 1 }, "Standardisering": { "count": 1 }, "Oppdal": { "count": 1 }, "Norske arkitekturinstitusjoner": { "count": 1 }, "Sparta": { "count": 1 }, "Kunsth\u00e5ndverk": { "count": 2 }, "Treskurd": { "count": 1 }, "Treskj\u00e6rere": { "count": 1 }, "Tysklands historie fra 1806 til 1918": { "count": 1 }, "Mexicos geografi": { "count": 1 }, "Selfamilien": { "count": 1 }, "Cystophora": { "count": 1 }, "Burundis geografi": { "count": 1 }, "Islands historie": { "count": 1 }, "Tegneserier": { "count": 1 }, "Birkenes": { "count": 1 }, "Humanetikk": { "count": 1 }, "Matretter": { "count": 2 }, "Supper": { "count": 2 }, " sauser og kraft": { "count": 2 }, "Ugandas historie": { "count": 1 }, "Erkjennelsesteori": { "count": 1 }, "Sveits\u2019 tyskspr\u00e5klig litteratur": { "count": 1 }, "Sveits\u2019 tyskspr\u00e5klig litteratur p\u00e5 1900-tallet": { "count": 1 }, "Popkunst og minimalisme": { "count": 1 }, "Klassisk ballett": { "count": 1 }, "Klassisk ballett: internasjonale kunstnere og kompanier": { "count": 1 }, "Inkludering og rettigheter": { "count": 1 }, "Likestilling og diskriminering": { "count": 1 }, "Kvinnebevegelse": { "count": 1 }, "Kvinnebevegelsen i Norge": { "count": 1 }, "Arkeologi i Asia": { "count": 1 }, "Cubas litteratur": { "count": 1 }, "Elektrokjemi": { "count": 1 }, "Norges litteratur 1960-2000": { "count": 3 }, "Nederlands litteratur": { "count": 1 }, "Forfattere i romerrikets litteratur": { "count": 1 }, "Forbrenningsmotorer": { "count": 2 }, "Vitenskapsteori": { "count": 1 }, "Vitenskapsteoretikere": { "count": 1 }, "Norsk lyrikk 1960-2000": { "count": 1 }, "Helserett": { "count": 1 }, "Klesplagg": { "count": 1 }, "Belgias geografi": { "count": 1 }, "Antarktis": { "count": 1 }, "Danseinstitusjoner": { "count": 1 }, "Irans geografi": { "count": 1 }, "V\u00e5rskrinneblomslekta": { "count": 1 }, "Motstandskampen i Norge": { "count": 1 }, "Skjell": { "count": 1 }, "Unionoida": { "count": 1 }, "Unionoidea": { "count": 1 }, "Elvemuslinger": { "count": 1 }, "Margaritifera": { "count": 2 }, "Klassisk arkeologi": { "count": 1 }, "Gresk arkeologi": { "count": 1 }, "Teknologi- og industrifag": { "count": 1 }, "Afrosoricida": { "count": 1 }, "Tenrecidae": { "count": 1 }, "Tysklands historie fra 1918 til 1933": { "count": 1 }, "Erstatningsrett": { "count": 1 }, "Trevirke": { "count": 1 }, "Sovjetunionens historie": { "count": 2 }, "Gjenstanders kulturhistorie": { "count": 2 }, "Dominicas geografi": { "count": 2 }, "B\u00f8keordenen": { "count": 1 }, "Bj\u00f8rkefamilien": { "count": 1 }, "Bj\u00f8rkeslekta": { "count": 1 }, "Metrikk": { "count": 1 }, "USAs historie 1920\u20131960": { "count": 2 }, "Energi og ressurs": { "count": 1 }, "Tysklands nyere litteratur": { "count": 1 }, "Libanons historie": { "count": 1 }, "B\u00e6rum": { "count": 1 }, "Brasils geografi": { "count": 1 }, "Norges historie fra 1300 til 1660": { "count": 1 }, "Natur og landemerker i USA": { "count": 2 }, "Kv\u00e6fjord": { "count": 1 }, "Fremmedord og l\u00e5nord": { "count": 2 }, "Lokalforvaltning": { "count": 1 }, "Brennevin": { "count": 1 }, "Drinker": { "count": 1 }, "Hest": { "count": 1 }, "Erteblomstordenen": { "count": 1 }, "Erteblomstfamilien": { "count": 1 }, "Acacia": { "count": 1 }, "Historiske biografier i norsk politikk": { "count": 1 }, "Fremmedord med latinsk og gresk opphav": { "count": 1 }, "B\u00e5tsfjord": { "count": 1 }, "Tidsskrifter": { "count": 1 }, "Romanias samtidshistorie": { "count": 1 }, "Fagretninger i sosiologi": { "count": 1 }, "Folkegrupper i S\u00f8r-Amerika": { "count": 1 }, "Norges historie generelt": { "count": 1 }, "Norsk polarhistorie": { "count": 1 }, "Tekstilkunst": { "count": 1 }, "Tekstilkunstnere": { "count": 1 }, "Arkeologer": { "count": 2 }, "Stabile grunnstoffer": { "count": 1 }, "Fiskenes anatomi og fysiologi": { "count": 1 }, "Vang": { "count": 1 }, "Sunnfjord": { "count": 1 }, "Samv\u00e6rsdans": { "count": 1 }, "Nicaraguas litteratur": { "count": 1 }, "Sulfid- og sulfatmineraler": { "count": 1 }, "Hardrock og heavy metal": { "count": 1 }, "Norsk hardrock og heavy metal": { "count": 1 }, "Aver\u00f8y": { "count": 1 }, "Sol og stjerner": { "count": 1 }, "Gloppen": { "count": 1 }, "Italiensk manierisme": { "count": 1 }, " barokk- og renessansekunst": { "count": 1 }, "Sakprosa": { "count": 1 }, "Sekksporesopper": { "count": 1 }, "Ursekksporesopper": { "count": 1 }, "Heksekostsopper": { "count": 1 }, "Religion i ulike land": { "count": 1 }, "Religion i Latin-Amerika": { "count": 1 }, "Italias nyere litteratur": { "count": 1 }, "Arkitekturteori og -metode": { "count": 1 }, "Bahrains geografi": { "count": 1 }, "Biografier i nyere norsk historie": { "count": 1 }, "Askvoll": { "count": 1 }, "\u00d8sterrikes litteratur p\u00e5 1900-tallet": { "count": 1 }, "Katt": { "count": 1 }, "Piggfinnefisker": { "count": 1 }, "Leppefiskfamilien": { "count": 1 }, "Ctenolabrus": { "count": 1 }, "Mykologi": { "count": 1 }, "Innholdsstoffer hos sopp": { "count": 1 }, "Fluesnapperfamilien": { "count": 1 }, "Luscinia": { "count": 1 }, "Colombias historie": { "count": 1 }, "\u00d8vrige indo-europeiske spr\u00e5k": { "count": 1 }, "Dannmarks historie 1814-1945": { "count": 1 }, "Arbeiderbevegelsens historie": { "count": 1 }, "Kameruns litteratur": { "count": 1 }, "Vannsport": { "count": 1 }, "Sv\u00f8mmesport": { "count": 1 }, "Abstrakt ekspresjonisme": { "count": 1 }, "Bulgarias historie": { "count": 1 }, "Storbritannia og Nord-Irlands litteratur p\u00e5 1800-tallet": { "count": 1 }, "Norske klassiske komponister og verker f\u00f8r 1900": { "count": 1 }, "Kirgisistans geografi": { "count": 1 }, "Panamas historie": { "count": 1 }, "Finlands geografi": { "count": 1 }, "Petroleumsprodukter": { "count": 1 }, "Teknisk kybernetikk": { "count": 1 }, "Dyregeografi": { "count": 1 }, "Verdens dyreliv": { "count": 1 }, "Minev\u00e5pen": { "count": 1 }, "Det bysantinske rike": { "count": 1 }, "Element\u00e6rpartikkelfysikk": { "count": 1 } } } } ``` </details> --- This dataset card was automatically generated using [MTEB](https://github.com/embeddings-benchmark/mteb)
Fhrozen/FSD50k	Fhrozen	2025-05-17T02:38:53Z	281	6	[ "task_categories:audio-classification", "annotations_creators:unknown", "language_creators:unknown", "source_datasets:unknown", "license:cc-by-4.0", "size_categories:10K<n<100K", "modality:audio", "arxiv:2010.00475", "region:us", "audio-slot-filling" ]	[ "audio-classification" ]	2022-05-06T08:51:56Z	0	--- annotations_creators: - unknown language_creators: - unknown license: cc-by-4.0 size_categories: - 10K<n<100K source_datasets: - unknown task_categories: - audio-classification task_ids: [] tags: - audio-slot-filling --- # Freesound Dataset 50k (FSD50K) ## Important This data set is a copy from the original one located at Zenodo. ## Dataset Description - Homepage: [FSD50K](https://zenodo.org/record/4060432) - Repository: [GitHub](https://github.com/edufonseca/FSD50K_baseline) - Paper: [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://arxiv.org/abs/2010.00475) - Leaderboard: [Paperswithcode Leaderboard](https://paperswithcode.com/dataset/fsd50k) ## Citation If you use the FSD50K dataset, or part of it, please cite our paper: >Eduardo Fonseca, Xavier Favory, Jordi Pons, Frederic Font, Xavier Serra. "FSD50K: an Open Dataset of Human-Labeled Sound Events", arXiv 2020. ### Data curators Eduardo Fonseca, Xavier Favory, Jordi Pons, Mercedes Collado, Ceren Can, Rachit Gupta, Javier Arredondo, Gary Avendano and Sara Fernandez ### Contact You are welcome to contact Eduardo Fonseca should you have any questions at [email protected]. ## About FSD50K Freesound Dataset 50k (or FSD50K for short) is an open dataset of human-labeled sound events containing 51,197 <a href="https://freesound.org/">Freesound</a> clips unequally distributed in 200 classes drawn from the <a href="https://research.google.com/audioset/ontology/index.html">AudioSet Ontology</a> [1]. FSD50K has been created at the <a href="https://www.upf.edu/web/mtg">Music Technology Group of Universitat Pompeu Fabra</a>. What follows is a brief summary of FSD50K's most important characteristics. Please have a look at our paper (especially Section 4) to extend the basic information provided here with relevant details for its usage, as well as discussion, limitations, applications and more. Basic characteristics: - FSD50K is composed mainly of sound events produced by physical sound sources and production mechanisms. - Following AudioSet Ontology’s main families, the FSD50K vocabulary encompasses mainly Human sounds, Sounds of things, Animal, Natural sounds and Music. - The dataset has 200 sound classes (144 leaf nodes and 56 intermediate nodes) hierarchically organized with a subset of the AudioSet Ontology. The vocabulary can be inspected in `vocabulary.csv` (see Files section below). - FSD50K contains 51,197 audio clips totalling 108.3 hours of audio. - The audio content has been manually labeled by humans following a data labeling process using the <a href="https://annotator.freesound.org/">Freesound Annotator</a> platform [2]. - Clips are of variable length from 0.3 to 30s, due to the diversity of the sound classes and the preferences of Freesound users when recording sounds. - Ground truth labels are provided at the clip-level (i.e., weak labels). - The dataset poses mainly a multi-label sound event classification problem (but also allows a variety of sound event research tasks, see Sec. 4D). - All clips are provided as uncompressed PCM 16 bit 44.1 kHz mono audio files. - The audio clips are grouped into a development (dev) set and an evaluation (eval) set such that they do not have clips from the same Freesound uploader. Dev set: - 40,966 audio clips totalling 80.4 hours of audio - Avg duration/clip: 7.1s - 114,271 smeared labels (i.e., labels propagated in the upwards direction to the root of the ontology) - Labels are correct but could be occasionally incomplete - A train/validation split is provided (Sec. 3H). If a different split is used, it should be specified for reproducibility and fair comparability of results (see Sec. 5C of our paper) Eval set: - 10,231 audio clips totalling 27.9 hours of audio - Avg duration/clip: 9.8s - 38,596 smeared labels - Eval set is labeled exhaustively (labels are correct and complete for the considered vocabulary) NOTE: All classes in FSD50K are represented in AudioSet, except `Crash cymbal`, `Human group actions`, `Human voice`, `Respiratory sounds`, and `Domestic sounds, home sounds`. ## License All audio clips in FSD50K are released under Creative Commons (CC) licenses. Each clip has its own license as defined by the clip uploader in Freesound, some of them requiring attribution to their original authors and some forbidding further commercial reuse. For attribution purposes and to facilitate attribution of these files to third parties, we include a mapping from the audio clips to their corresponding licenses. The licenses are specified in the files `dev_clips_info_FSD50K.json` and `eval_clips_info_FSD50K.json`. These licenses are CC0, CC-BY, CC-BY-NC and CC Sampling+. In addition, FSD50K as a whole is the result of a curation process and it has an additional license: FSD50K is released under <a href="https://creativecommons.org/licenses/by/4.0/">CC-BY</a>. This license is specified in the `LICENSE-DATASET` file downloaded with the `FSD50K.doc` zip file. ## Files FSD50K can be downloaded as a series of zip files with the following directory structure: <div class="highlight"><pre><span></span>root │ └───clips/ Audio clips │ │ │ └─── dev/ Audio clips in the dev set │ │ │ └─── eval/ Audio clips in the eval set │ └───labels/ Files for FSD50K's ground truth │ │ │ └─── dev.csv Ground truth for the dev set │ │ │ └─── eval.csv Ground truth for the eval set │ │ │ └─── vocabulary.csv List of 200 sound classes in FSD50K │ └───metadata/ Files for additional metadata │ │ │ └─── class_info_FSD50K.json Metadata about the sound classes │ │ │ └─── dev_clips_info_FSD50K.json Metadata about the dev clips │ │ │ └─── eval_clips_info_FSD50K.json Metadata about the eval clips │ │ │ └─── pp_pnp_ratings_FSD50K.json PP/PNP ratings │ │ │ └─── collection/ Files for the sound collection format │ │ └───README.md The dataset description file that you are reading │ └───LICENSE-DATASET License of the FSD50K dataset as an entity </pre></div> Each row (i.e. audio clip) of `dev.csv` contains the following information: - `fname`: the file name without the `.wav` extension, e.g., the fname `64760` corresponds to the file `64760.wav` in disk. This number is the Freesound id. We always use Freesound ids as filenames. - `labels`: the class labels (i.e., the ground truth). Note these class labels are smeared, i.e., the labels have been propagated in the upwards direction to the root of the ontology. More details about the label smearing process can be found in Appendix D of our paper. - `mids`: the Freebase identifiers corresponding to the class labels, as defined in the <a href="https://github.com/audioset/ontology/blob/master/ontology.json">AudioSet Ontology specification</a> - `split`: whether the clip belongs to train or val (see paper for details on the proposed split) Rows in `eval.csv` follow the same format, except that there is no `split` column. NOTE: We use a slightly different format than AudioSet for the naming of class labels in order to avoid potential problems with spaces, commas, etc. Example: we use `Accelerating_and_revving_and_vroom` instead of the original `Accelerating, revving, vroom`. You can go back to the original AudioSet naming using the information provided in `vocabulary.csv` (class label and mid for the 200 classes of FSD50K) and the <a href="https://github.com/audioset/ontology/blob/master/ontology.json">AudioSet Ontology specification</a>. ### Files with additional metadata (metadata/) To allow a variety of analysis and approaches with FSD50K, we provide the following metadata: 1. `class_info_FSD50K.json`: python dictionary where each entry corresponds to one sound class and contains: `FAQs` utilized during the annotation of the class, `examples` (representative audio clips), and `verification_examples` (audio clips presented to raters during annotation as a quality control mechanism). Audio clips are described by the Freesound id. NOTE: It may be that some of these examples are not included in the FSD50K release. 2. `dev_clips_info_FSD50K.json`: python dictionary where each entry corresponds to one dev clip and contains: title, description, tags, clip license, and the uploader name. All these metadata are provided by the uploader. 3. `eval_clips_info_FSD50K.json`: same as before, but with eval clips. 4. `pp_pnp_ratings.json`: python dictionary where each entry corresponds to one clip in the dataset and contains the PP/PNP ratings for the labels associated with the clip. More specifically, these ratings are gathered for the labels validated in the validation task (Sec. 3 of paper). This file includes 59,485 labels for the 51,197 clips in FSD50K. Out of these labels: - 56,095 labels have inter-annotator agreement (PP twice, or PNP twice). Each of these combinations can be occasionally accompanied by other (non-positive) ratings. - 3390 labels feature other rating configurations such as i) only one PP rating and one PNP rating (and nothing else). This can be considered inter-annotator agreement at the ``Present” level; ii) only one PP rating (and nothing else); iii) only one PNP rating (and nothing else). Ratings' legend: PP=1; PNP=0.5; U=0; NP=-1. NOTE: The PP/PNP ratings have been provided in the validation task. Subsequently, a subset of these clips corresponding to the eval set was exhaustively labeled in the refinement task, hence receiving additional labels in many cases. For these eval clips, you might want to check their labels in `eval.csv` in order to have more info about their audio content (see Sec. 3 for details). 5. `collection/`: This folder contains metadata for what we call the *sound collection format. This format consists of the raw annotations gathered, featuring all generated class labels without any restriction. We provide the collection* format to make available some annotations that do not appear in the FSD50K ground truth release. This typically happens in the case of classes for which we gathered human-provided annotations, but that were discarded in the FSD50K release due to data scarcity (more specifically, they were merged with their parents). In other words, the main purpose of the `collection` format is to make available annotations for tiny classes. The format of these files in analogous to that of the files in `FSD50K.ground_truth/`. A couple of examples show the differences between collection and ground truth formats: `clip`: `labels_in_collection` -- `labels_in_ground_truth` `51690`: `Owl` -- `Bird,Wild_Animal,Animal` `190579`: `Toothbrush,Electric_toothbrush` -- `Domestic_sounds_and_home_sounds` In the first example, raters provided the label `Owl`. However, due to data scarcity, `Owl` labels were merged into their parent `Bird`. Then, labels `Wild_Animal,Animal` were added via label propagation (smearing). The second example shows one of the most extreme cases, where raters provided the labels `Electric_toothbrush,Toothbrush`, which both had few data. Hence, they were merged into Toothbrush's parent, which unfortunately is `Domestic_sounds_and_home_sounds` (a rather vague class containing a variety of children sound classes). NOTE: Labels in the collection format are not smeared. NOTE: While in FSD50K's ground truth the vocabulary encompasses 200 classes (common for dev and eval), since the collection format is composed of raw annotations, the vocabulary here is much larger (over 350 classes), and it is slightly different in dev and eval. For further questions, please contact [email protected], or join the <a href="https://groups.google.com/g/freesound-annotator">freesound-annotator Google Group</a>. ## Download Clone this repository: ``` git clone https://huggingface.co/Fhrozen/FSD50k ``` ## Baseline System Several baseline systems for FSD50K are available at <a href="https://github.com/edufonseca/FSD50K_baseline">https://github.com/edufonseca/FSD50K_baseline</a>. The experiments are described in Sec 5 of our paper. ## References and links [1] Jort F Gemmeke, Daniel PW Ellis, Dylan Freedman, Aren Jansen, Wade Lawrence, R Channing Moore, Manoj Plakal, and Marvin Ritter. "Audio set: An ontology and human-labeled dataset for audio events." In Proceedings of the International Conference on Acoustics, Speech and Signal Processing, 2017. [<a href="https://ai.google/research/pubs/pub45857">PDF</a>] [2] Eduardo Fonseca, Jordi Pons, Xavier Favory, Frederic Font, Dmitry Bogdanov, Andres Ferraro, Sergio Oramas, Alastair Porter, and Xavier Serra. "Freesound Datasets: A Platform for the Creation of Open Audio Datasets." In Proceedings of the International Conference on Music Information Retrieval, 2017. [<a href="https://repositori.upf.edu/bitstream/handle/10230/33299/fonseca_ismir17_freesound.pdf">PDF</a>] Companion site for FSD50K: <a href="https://annotator.freesound.org/fsd/release/FSD50K/">https://annotator.freesound.org/fsd/release/FSD50K/</a> Freesound Annotator: <a href="https://annotator.freesound.org/">https://annotator.freesound.org/</a> Freesound: <a href="https://freesound.org">https://freesound.org</a> Eduardo Fonseca's personal website: <a href="http://www.eduardofonseca.net/">http://www.eduardofonseca.net/</a> More datasets collected by us: <a href="http://www.eduardofonseca.net/datasets/">http://www.eduardofonseca.net/datasets/</a> ## Acknowledgments The authors would like to thank everyone who contributed to FSD50K with annotations, and especially Mercedes Collado, Ceren Can, Rachit Gupta, Javier Arredondo, Gary Avendano and Sara Fernandez for their commitment and perseverance. The authors would also like to thank Daniel P.W. Ellis and Manoj Plakal from Google Research for valuable discussions. This work is partially supported by the European Union’s Horizon 2020 research and innovation programme under grant agreement No 688382 <a href="https://www.audiocommons.org/">AudioCommons</a>, and two Google Faculty Research Awards <a href="https://ai.googleblog.com/2018/03/google-faculty-research-awards-2017.html">2017</a> and <a href="https://ai.googleblog.com/2019/03/google-faculty-research-awards-2018.html">2018</a>, and the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502).
nickfuryavg/Kathbath-Audio-44100-Batch-28	nickfuryavg	2025-03-25T12:04:36Z	15	0	[ "size_categories:1K<n<10K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-03-25T12:04:21Z	0	--- dataset_info: features: - name: fname dtype: string - name: text dtype: string - name: audio_filepath dtype: audio: sampling_rate: 44100 - name: gender dtype: string splits: - name: train num_bytes: 158271555.0 num_examples: 1000 download_size: 155299101 dataset_size: 158271555.0 configs: - config_name: default data_files: - split: train path: data/train-* ---
ZHLiu627/updated-code-qwen7-edu	ZHLiu627	2025-02-21T18:07:42Z	26	0	[ "size_categories:10K<n<100K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-02-21T18:07:35Z	0	--- dataset_info: features: - name: seq_id dtype: int64 - name: instruction dtype: string - name: output dtype: string - name: code dtype: string - name: entry_point dtype: string - name: testcase sequence: string - name: prompt dtype: string - name: new_prompt dtype: string - name: responses sequence: string - name: rewards sequence: float64 - name: mean_reward dtype: float64 splits: - name: train num_bytes: 427086591 num_examples: 75626 download_size: 148777252 dataset_size: 427086591 configs: - config_name: default data_files: - split: train path: data/train-* ---
Asap7772/safety_nofix_evalbase_vllmgen__3212_3670	Asap7772	2025-03-02T23:44:11Z	17	0	[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-03-02T23:44:00Z	0	--- dataset_info: features: - name: chat_y_w list: - name: content dtype: string - name: role dtype: string - name: chat_y_l list: - name: content dtype: string - name: role dtype: string - name: reward_yw sequence: float64 - name: reward_yl sequence: float64 - name: question_list sequence: string - name: response_yw_list sequence: string - name: response_yl_list sequence: string - name: source dtype: string - name: query dtype: string - name: completions sequence: string splits: - name: train num_bytes: 42298574 num_examples: 458 download_size: 19531732 dataset_size: 42298574 configs: - config_name: default data_files: - split: train path: data/train-* ---
avdeep/half_sanskrit_speakerembeddings	avdeep	2025-02-13T18:17:50Z	16	0	[ "size_categories:10K<n<100K", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-02-13T18:16:19Z	0	--- dataset_info: features: - name: input_ids sequence: int32 - name: labels sequence: sequence: float32 - name: speaker_embeddings sequence: float32 splits: - name: train num_bytes: 2460357452 num_examples: 18607 download_size: 2456505911 dataset_size: 2460357452 configs: - config_name: default data_files: - split: train path: data/train-* ---
Cadenza-Labs/alpaca_Mistral-Small-3.1-24B-Instruct	Cadenza-Labs	2025-05-24T12:27:33Z	14	0	[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-05-23T13:26:27Z	0	--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: dishonest dtype: bool splits: - name: train num_bytes: 7625123 num_examples: 7210 download_size: 4196413 dataset_size: 7625123 configs: - config_name: default data_files: - split: train path: data/train-* ---
cestwc/SG-subzone-poi-estate-share	cestwc	2025-01-15T23:52:37Z	53	0	[ "size_categories:1M<n<10M", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-01-15T23:52:15Z	0	--- dataset_info: features: - name: id dtype: int64 - name: text dtype: string - name: source dtype: string - name: truncated dtype: bool - name: latitude dtype: float32 - name: longitude dtype: float32 - name: year_created_at dtype: int64 - name: month_created_at dtype: int64 - name: day_created_at dtype: int64 - name: weekday_created_at dtype: int64 - name: hour_created_at dtype: int64 - name: minute_created_at dtype: int64 - name: subzone dtype: string - name: polarity_score dtype: float32 - name: label_manual dtype: int64 - name: label_T01 dtype: int64 - name: label_bart dtype: float32 - name: label_T02 dtype: int64 - name: num_keywords dtype: int64 - name: preprocess-1 dtype: string - name: preprocess-2 dtype: string - name: label_llama dtype: int64 - name: label_c dtype: bool - name: llama-2 dtype: string - name: relatedness dtype: float64 - name: label dtype: float64 - name: planning_area dtype: class_label: names: '0': '' '1': ANG MO KIO '2': BEDOK '3': BISHAN '4': BOON LAY '5': BUKIT BATOK '6': BUKIT MERAH '7': BUKIT PANJANG '8': BUKIT TIMAH '9': CENTRAL WATER CATCHMENT '10': CHANGI '11': CHOA CHU KANG '12': CLEMENTI '13': DOWNTOWN CORE '14': GEYLANG '15': HOUGANG '16': JURONG EAST '17': JURONG WEST '18': KALLANG '19': LIM CHU KANG '20': MANDAI '21': MARINA EAST '22': MARINA SOUTH '23': MARINE PARADE '24': MUSEUM '25': NEWTON '26': NORTH-EASTERN ISLANDS '27': NOVENA '28': ORCHARD '29': OUTRAM '30': PASIR RIS '31': PAYA LEBAR '32': PIONEER '33': PUNGGOL '34': QUEENSTOWN '35': RIVER VALLEY '36': ROCHOR '37': SELETAR '38': SEMBAWANG '39': SENGKANG '40': SERANGOON '41': SIMPANG '42': SINGAPORE RIVER '43': SOUTHERN ISLANDS '44': STRAITS VIEW '45': SUNGEI KADUT '46': TAMPINES '47': TANGLIN '48': TENGAH '49': TOA PAYOH '50': TUAS '51': WESTERN ISLANDS '52': WESTERN WATER CATCHMENT '53': WOODLANDS '54': YISHUN - name: category dtype: class_label: names: '0': Animals and Birds '1': Cleanliness '2': Connectivity Related Infrastructure '3': Enforcement Matters '4': General Infrastructure/Facilities '5': Greenery '6': Illegal Parking '7': Neighbour Issues '8': Noise '9': Pests '10': Pollution '11': Public Housing Infrastructure (Excl Lifts) '12': Public Housing Lifts '13': '' splits: - name: train num_bytes: 1011861795 num_examples: 1025135 download_size: 321895097 dataset_size: 1011861795 configs: - config_name: default data_files: - split: train path: data/train-* ---
1231czx/rlhflow_mix_w_dart_math	1231czx	2024-10-18T15:25:22Z	21	0	[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2024-10-18T15:23:36Z	0	--- dataset_info: features: - name: conversations list: - name: content dtype: string - name: role dtype: string - name: source dtype: string - name: conversation_id dtype: int64 splits: - name: train num_bytes: 2793967415.7409267 num_examples: 1831548 download_size: 1367201281 dataset_size: 2793967415.7409267 configs: - config_name: default data_files: - split: train path: data/train-* ---
mlfoundations-dev/oh_teknium_scaling_down_random_1.0	mlfoundations-dev	2024-12-21T13:21:40Z	14	0	[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2024-12-21T13:21:12Z	0	--- dataset_info: features: - name: conversations list: - name: from dtype: string - name: value dtype: string - name: weight dtype: float64 splits: - name: train num_bytes: 1605295072 num_examples: 1001551 download_size: 779986988 dataset_size: 1605295072 configs: - config_name: default data_files: - split: train path: data/train-* ---
ZixuanKe/cfa_extracted_exercise_sup_sample_from_policy_v1_1_rpo_iter_1_dpo_binarized_val_chunk_5	ZixuanKe	2024-11-16T06:45:34Z	19	0	[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2024-11-16T06:45:33Z	0	--- dataset_info: features: - name: prompt dtype: string - name: rejected dtype: string - name: chosen dtype: string splits: - name: train num_bytes: 7156 num_examples: 6 download_size: 12097 dataset_size: 7156 configs: - config_name: default data_files: - split: train path: data/train-* ---
fhai50032/Math-Pretrain-Packed-QTK-81K	fhai50032	2025-03-10T15:43:31Z	15	1	[ "size_categories:1M<n<10M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-03-10T15:39:13Z	0	--- dataset_info: features: - name: input_ids sequence: int32 - name: attention_mask sequence: int8 splits: - name: train num_bytes: 18755356704 num_examples: 1830148 download_size: 5894246453 dataset_size: 18755356704 configs: - config_name: default data_files: - split: train path: data/train-* ---
kadirnar/combined-turkish-dataset-v5-unsloth	kadirnar	2025-04-02T22:21:55Z	18	0	[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-04-02T18:02:58Z	0	--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 1464850790 num_examples: 1054470 download_size: 770824035 dataset_size: 1464850790 configs: - config_name: default data_files: - split: train path: data/train-* ---
mandanya/logseq-query-clojure	mandanya	2024-11-27T11:07:44Z	17	0	[ "license:apache-2.0", "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2024-11-27T05:08:36Z	0	--- license: apache-2.0 dataset_info: features: - name: prompt dtype: string - name: query dtype: string - name: synthetic dtype: int64 - name: orig_index dtype: float64 splits: - name: train num_bytes: 385651 num_examples: 801 - name: test num_bytes: 40982 num_examples: 81 download_size: 89211 dataset_size: 426633 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
JesusCrist/mt_bench_prompts	JesusCrist	2025-05-28T06:38:29Z	0	0	[ "license:mit", "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-05-28T05:54:42Z	0	--- license: mit configs: - config_name: default data_files: - split: train path: data/train-* dataset_info: features: - name: question_id dtype: int64 - name: category dtype: string - name: turns sequence: string - name: reference sequence: string - name: gpt4_reference sequence: string splits: - name: train num_bytes: 91373 num_examples: 80 download_size: 53582 dataset_size: 91373 ---
masaki-sakata/wikidata_descriptions	masaki-sakata	2025-05-21T13:58:01Z	0	0	[ "language:en", "license:mit", "region:us", "Wikidata", "Wikipedia", "Description", "Entity", "QID", "Knowledge" ]	[]	2025-05-21T13:30:44Z	0	--- dataset_info: features: - name: wiki_title dtype: string - name: qid dtype: string - name: description dtype: string splits: - name: en num_bytes: 1938197 num_examples: 26205 download_size: 1256160 dataset_size: 1938197 configs: - config_name: default data_files: - split: en path: data/en-* license: mit language: - en tags: - Wikidata - Wikipedia - Description - Entity - QID - Knowledge --- # Wikidata Descriptions Dataset `wikidata_descriptions` pairs English Wikipedia article titles (`wiki_title`) and their Wikidata IDs (`qid`) with the English "description" available in Wikidata. The corpus contains 26 205 entities. Wikidata descriptions are short, one-line summaries that concisely state what an entity is. They can be used as lightweight contextual information in entity linking, search, question answering, knowledge-graph completion and many other NLP / IR tasks. --- ## Dataset Structure ```python from datasets import load_dataset ds = load_dataset("masaki-sakata/wikidata_descriptions", split="en") print(ds) # Dataset({ # features: ['wiki_title', 'qid', 'description'], # num_rows: 26205 # }) ``` Field description: \| column \| type \| description \| \|--------------\|--------\|--------------------------------------------------------------------\| \| `wiki_title` \| str \| Title of the corresponding English Wikipedia article \| \| `qid` \| str \| Wikidata identifier, e.g. `Q7156` \| \| `description`\| str \| English one-line description provided by Wikidata (CC-0) \| Example: ```json { "wiki_title": "Michael Jordan", "qid": "Q41421", "description": "American basketball player and businessman (born 1963)" } ``` ## Quick Usage Example ```python from datasets import load_dataset ds = load_dataset("masaki-sakata/wikidata_descriptions", split="en") # Retrieve the first 3 entities for record in ds.select(range(3)): print(record) ``` --- ## Source & Construction 1. Seed list [`masaki-sakata/entity_popularity`](https://huggingface.co/datasets/masaki-sakata/entity_popularity) (English split) provides `wiki_title` and `qid`. 2. Enrichment For every `qid`, we queried the Wikidata API (`wbgetentities`, language = `en`) and kept the English description if present. 3. Filtering Rows with empty or missing descriptions were dropped, resulting in 26 205 items. 4. License All descriptions originate from Wikidata and are released under CC-0. The dataset as a whole is distributed under the MIT License. ---
lianghsun/Everything-Instruct-Multilingual-DPO	lianghsun	2024-12-10T01:06:43Z	76	1	[ "language:en", "language:ru", "language:zh", "language:ko", "language:ur", "language:la", "language:ar", "language:de", "language:es", "language:fr", "language:hi", "language:it", "language:ja", "language:nl", "language:pt", "license:cc-by-nc-sa-4.0", "size_categories:1M<n<10M", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2305.18290", "region:us", "sft", "dpo" ]	[]	2024-12-05T01:37:25Z	0	--- license: cc-by-nc-sa-4.0 language: - en - ru - zh - ko - ur - la - ar - de - es - fr - hi - it - ja - nl - pt tags: - sft - dpo size_categories: - 1M<n<10M --- # Dataset Card for lianghsun/Everything-Instruct-Multilingual-DPO <!-- Provide a quick summary of the dataset. --> ## Dataset Details ### Dataset Description <!-- Provide a longer summary of what this dataset is. --> 這個資料集是分叉於 [rombodawg/Everything_Instruct_Multilingual](https://huggingface.co/datasets/rombodawg/Everything_Instruct_Multilingual)，但在中文回答的部份透過 [opencc-python](https://github.com/yichen0831/opencc-python) 將簡體中文（zh-cn）轉成繁體中文（zh-tw）。除此之外，我們將資料集升級成具有 [DPO](https://arxiv.org/abs/2305.18290) 欄位，該 `rejected` 回覆是由 [lianghsun/Llama-3.2-Taiwan-3B-Instruct](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B-Instruct) `v2024.11.27` 生成，此資料集將用於 lianghsun/Llama-3.2-Taiwan-3B-Instruct 的 DPO 階段。 - Curated by: [Huang Liang Hsun](https://www.linkedin.com/in/lianghsunhuang/?locale=en_US) - Language(s) (NLP): multilingual - License: cc-by-nc-sa-4.0 ### Dataset Sources <!-- Provide the basic links for the dataset. --> - Repository: [lianghsun/Everything-Instruct-Multilingual](https://huggingface.co/datasets/lianghsun/Everything-Instruct-Multilingual/) ## Uses <!-- Address questions around how the dataset is intended to be used. --> ### Direct Use <!-- This section describes suitable use cases for the dataset. --> 本資料集可以用在 SFT 與 DPO 的訓練階段。 ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> 本資料集並不適合用在評測集或者是任何事實審核使用。 ## Dataset Structure <!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. --> ```yaml { "instruction": "", "input": "", "rejected": "" } ``` ## Dataset Creation ### Curation Rationale <!-- Motivation for the creation of this dataset. --> 具有多國語系的指令資料集鮮少，更不用說多國語系的偏好資料集（Preference dataset），故本資料集以 [rombodawg/Everything_Instruct_Multilingual](https://huggingface.co/datasets/rombodawg/Everything_Instruct_Multilingual) 為基底資料集（foundation dataset），新增拒絕（rejected）回覆，使資料集更加全面，用戶可利用此資料集訓練模型進行多語系偏好學習。 ### Source Data <!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). --> #### Data Collection and Processing <!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. --> 1. 簡體中文轉繁體中文：本資料集將簡體中文轉成繁體中文。 2. 生成拒絕回覆：透過模型生成拒絕回覆，以建立偏好資料集。 #### Who are the source data producers? <!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. --> - Foundation dataset: [rombodawg/Everything_Instruct_Multilingual](https://huggingface.co/datasets/rombodawg/Everything_Instruct_Multilingual) - Rejected dataset: [lianghsun/Llama-3.2-Taiwan-3B-Instruct](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B-Instruct) ### Annotations [optional] <!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. --> #### Annotation process <!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. --> 無。 #### Who are the annotators? <!-- This section describes the people or systems who created the annotations. --> 無。 #### Personal and Sensitive Information <!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. --> 我們未針對原始資料進行 PII 檢測，但曾經收過 Hugging Face 系統信通知原始資料集內含有密鑰相關，請使用者再自行檢測。 ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> 任何人使用此資料集都應該要注意，原始資料內可能含有不同立場和情境的言論，請小心使用。 ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations. ## Citation [optional] <!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. --> ```yaml @misc{huang2024everything, author = {Huang, Liang Hsun}, title = {Everything-Instruct-Multilingual-DPO}, year = {2024}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/datasets/lianghsun/Everything-Instruct-Multilingual-DPO}}, note = {多國語系的指令服從資料集，可用於 SFT 或 DPO 訓練} } ``` ## More Information 本人僅能檢視繁體中文的部分，原始資料集含有中文的部分，大部分都是被要求翻譯成為中文（output），但經檢視中文的文本品質並不是很高水準，更甚至可能原始產生輸出的模型之中文能力低落，建議可以將有中文輸出的欄位刪除後再進行訓練。註：至此至今，我開始也懷疑原始資料集的多國語系指令回覆，是否也是低品質？但如果你缺少一個多國語系的指令資料集，這將是一個很好入門的資料集。 ## Dataset Card Authors [Huang Liang Hsun](https://www.linkedin.com/in/lianghsunhuang/?locale=en_US) ## Dataset Card Contact [Huang Liang Hsun](https://www.linkedin.com/in/lianghsunhuang/?locale=en_US)
abar-uwc/vaani-bihar_saharsa-cleaned	abar-uwc	2025-05-29T09:50:56Z	42	0	[ "size_categories:1K<n<10K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-05-29T09:50:27Z	0	--- dataset_info: features: - name: audio dtype: audio - name: language dtype: string - name: languagesKnown dtype: string - name: gender dtype: string - name: state dtype: string - name: district dtype: string - name: pincode dtype: int64 - name: stay(years) dtype: string - name: isTranscriptionAvailable dtype: string - name: transcript dtype: string - name: referenceImage dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 966513063.93 num_examples: 4701 download_size: 949827251 dataset_size: 966513063.93 configs: - config_name: default data_files: - split: train path: data/train-* ---
HanyangMed/final_diagnosis_medqa	HanyangMed	2025-02-16T17:34:35Z	22	0	[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-02-15T08:46:43Z	0	--- dataset_info: features: - name: question dtype: string - name: options dtype: string - name: answer dtype: string - name: meta_info dtype: string - name: answer_idx dtype: string splits: - name: train num_bytes: 2056320.318769505 num_examples: 3658 - name: test num_bytes: 229019.69477911646 num_examples: 416 download_size: 1487566 dataset_size: 2285340.0135486214 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
BarryFutureman/vpt_data_8xx_shard0214	BarryFutureman	2025-06-11T02:26:04Z	0	0	[ "task_categories:robotics", "license:apache-2.0", "size_categories:10K<n<100K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us", "LeRobot" ]	[ "robotics" ]	2025-06-11T02:24:32Z	0	--- license: apache-2.0 task_categories: - robotics tags: - LeRobot configs: - config_name: default data_files: data//.parquet --- This dataset was created using [LeRobot](https://github.com/huggingface/lerobot). ## Dataset Description - Homepage: [More Information Needed] - Paper: [More Information Needed] - License: apache-2.0 ## Dataset Structure [meta/info.json](meta/info.json): ```json { "codebase_version": "v2.1", "robot_type": null, "total_episodes": 10, "total_frames": 42289, "total_tasks": 1, "total_videos": 0, "total_chunks": 1, "chunks_size": 1000, "fps": 20, "splits": { "train": "0:10" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4", "features": { "observation.image": { "dtype": "image", "shape": [ 3, 360, 640 ], "names": [ "channel", "height", "width" ] }, "action": { "dtype": "string", "shape": [ 1 ], "names": null }, "timestamp": { "dtype": "float32", "shape": [ 1 ], "names": null }, "frame_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "episode_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "task_index": { "dtype": "int64", "shape": [ 1 ], "names": null } } } ``` ## Citation BibTeX: ```bibtex [More Information Needed] ```
marco-schouten/1_shape	marco-schouten	2024-11-28T15:05:19Z	15	0	[ "size_categories:n<1K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2024-11-28T14:57:26Z	0	--- dataset_info: features: - name: input_image dtype: image - name: edit_prompt dtype: string - name: edited_image dtype: image splits: - name: train num_bytes: 100968.0 num_examples: 27 download_size: 50708 dataset_size: 100968.0 configs: - config_name: default data_files: - split: train path: data/train-* ---
yvan-pimi/swahili-child-assessment	yvan-pimi	2025-06-10T12:05:13Z	63	0	[ "size_categories:n<1K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]	[]	2025-06-10T12:05:05Z	0	--- dataset_info: features: - name: audio dtype: audio: sampling_rate: 16000 - name: sr dtype: int64 - name: grade-level dtype: int64 - name: wpm dtype: int64 - name: acc dtype: int64 - name: grade dtype: int64 - name: mistakes dtype: int64 - name: sentence dtype: string splits: - name: train num_bytes: 25860353.0 num_examples: 75 download_size: 19737032 dataset_size: 25860353.0 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "swahili-child-assessment" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

junnystateofmind/testing_refuel_5_turns_only_ckp_1

junnystateofmind

2024-11-23T14:42:02Z

14

0

[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2024-11-23T14:42:00Z

0

--- dataset_info: features: - name: combined_data struct: - name: narrative dtype: string - name: trajectory list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 37130 num_examples: 5 download_size: 20861 dataset_size: 37130 configs: - config_name: default data_files: - split: train path: data/train-* ---

dsrtrain/qwq2ep_raft_iter1_gen_with_rewards

dsrtrain

2025-02-12T18:37:22Z

16

0

[ "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-02-12T18:37:01Z

0

--- dataset_info: features: - name: idx dtype: int64 - name: prompt dtype: string - name: answers sequence: string - name: gt struct: - name: ground_truth dtype: string - name: style dtype: string - name: rewards sequence: bool splits: - name: train num_bytes: 1010939991 num_examples: 20000 download_size: 373038950 dataset_size: 1010939991 configs: - config_name: default data_files: - split: train path: data/train-* ---

mlfoundations-dev/d1_math_multiple_languages_10k

mlfoundations-dev

2025-05-01T16:33:51Z

0

[ "size_categories:1K<n<10K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-05-01T16:28:39Z

0

--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: instruction_seed dtype: string - name: response_seed dtype: string - name: _source dtype: string - name: gpt41_mini_response dtype: string - name: __original_row_idx dtype: int64 - name: length dtype: int64 - name: ms_id dtype: int64 - name: reasoning sequence: string - name: deepseek_solution sequence: string - name: final_reasoning_trace sequence: string - name: correct sequence: bool - name: classifier_reasoning dtype: string - name: _majority_responses sequence: string - name: verified_final_reasoning_trace dtype: string - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 18188281981.012657 num_examples: 10000 download_size: 7437623502 dataset_size: 18188281981.012657 configs: - config_name: default data_files: - split: train path: data/train-* ---

mlazniewski/mlazniewski_octopus_train_cellines

mlazniewski

2025-06-06T12:25:18Z

0

[ "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-06-06T12:25:02Z

0

--- dataset_info: - config_name: disease_questions features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 324497 num_examples: 2254 download_size: 66737 dataset_size: 324497 - config_name: lineage_questions features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 536022 num_examples: 3940 download_size: 106817 dataset_size: 536022 - config_name: mutations_questions features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 491417 num_examples: 3050 download_size: 97498 dataset_size: 491417 - config_name: site_questions features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 477375 num_examples: 3942 download_size: 102655 dataset_size: 477375 - config_name: transformant_questions features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 47084 num_examples: 340 download_size: 11198 dataset_size: 47084 configs: - config_name: disease_questions data_files: - split: train path: disease_questions/train-* - config_name: lineage_questions data_files: - split: train path: lineage_questions/train-* - config_name: mutations_questions data_files: - split: train path: mutations_questions/train-* - config_name: site_questions data_files: - split: train path: site_questions/train-* - config_name: transformant_questions data_files: - split: train path: transformant_questions/train-* ---

emrecn/ShortData

emrecn

2025-05-16T13:03:57Z

0

[ "size_categories:100K<n<1M", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-05-16T08:35:23Z

0

--- dataset_info: features: - name: id dtype: string - name: image dtype: image - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 24684536649.125 num_examples: 299967 download_size: 24646621713 dataset_size: 24684536649.125 configs: - config_name: default data_files: - split: train path: data/train-* ---

colabfit/HME21_train

colabfit

2025-05-14T01:49:50Z

0

[ "license:cc-by-4.0", "region:us", "molecular dynamics", "mlip", "interatomic potential" ]

[]

2025-05-14T01:49:48Z

0

--- configs: - config_name: default data_files: "main/*.parquet" license: cc-by-4.0 tags: - molecular dynamics - mlip - interatomic potential pretty_name: HME21 train --- ### Cite this dataset Takamoto, S., Shinagawa, C., Motoki, D., Nakago, K., Li, W., Kurata, I., Watanabe, T., Yayama, Y., Iriguchi, H., Asano, Y., Onodera, T., Ishii, T., Kudo, T., Ono, H., Sawada, R., Ishitani, R., Ong, M., Yamaguchi, T., Kataoka, T., Hayashi, A., Charoenphakdee, N., and Ibuka, T. _HME21 train_. ColabFit, 2023. https://doi.org/10.60732/845cc1b5 ### View on the ColabFit Exchange https://materials.colabfit.org/id/DS_jhfis7syauhm_0 # Dataset Name HME21 train ### Description The training set from HME21. The high-temperature multi-element 2021 (HME21) dataset comprises approximately 25,000 configurations, including 37 elements, used in the training of a universal NNP called PreFerential Potential (PFP). The dataset specifically contains disordered and unstable structures, and structures that include irregular substitutions, as well as varied temperature and density. <br>Additional details stored in dataset columns prepended with "dataset_". ### Dataset authors So Takamoto, Chikashi Shinagawa, Daisuke Motoki, Kosuke Nakago, Wenwen Li, Iori Kurata, Taku Watanabe, Yoshihiro Yayama, Hiroki Iriguchi, Yusuke Asano, Tasuku Onodera, Takafumi Ishii, Takao Kudo, Hideki Ono, Ryohto Sawada, Ryuichiro Ishitani, Marc Ong, Taiki Yamaguchi, Toshiki Kataoka, Akihide Hayashi, Nontawat Charoenphakdee, Takeshi Ibuka ### Publication https://doi.org/10.1038/s41467-022-30687-9 ### Original data link https://doi.org/10.6084/m9.figshare.19658538.v2 ### License CC-BY-4.0 ### Number of unique molecular configurations 19956 ### Number of atoms 555050 ### Elements included Pb, Ba, Co, Cr, Cu, Mg, Mn, Mo, Ni, O, S, Sc, Si, V, Zn, Fe, Ir, Li, P, Pt, Ru, Sn, Ca, F, Au, Cl, H, Ag, C, In, K, N, Pd, Rh, Na, Ti, Al ### Properties included energy, atomic forces, cauchy stress

abhinav302019/olympiad_data_296

abhinav302019

2025-03-05T15:32:01Z

18

0

[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-03-05T15:31:58Z

0

--- dataset_info: features: - name: problem dtype: string - name: Known_Solution dtype: string - name: Known_Answer dtype: string - name: Generated_Solution dtype: string - name: Generated_Answer dtype: string - name: Judge_Evaluation dtype: string - name: Judge_Rating dtype: string - name: Judge_Justification dtype: string splits: - name: train num_bytes: 81293 num_examples: 10 download_size: 48130 dataset_size: 81293 configs: - config_name: default data_files: - split: train path: data/train-* ---

yasserrmd/food-safety-classifications

yasserrmd

2025-01-06T04:33:24Z

48

1

[ "language:en", "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "library:distilabel", "region:us", "synthetic", "distilabel", "rlaif", "datacraft" ]

[]

2025-01-04T06:49:56Z

0

--- language: - en size_categories: n<1K dataset_info: features: - name: text dtype: string - name: label dtype: class_label: names: '0': food-safety '1': non-food-safety splits: - name: train num_bytes: 76322 num_examples: 439 download_size: 34724 dataset_size: 76322 configs: - config_name: default data_files: - split: train path: data/train-* tags: - synthetic - distilabel - rlaif - datacraft --- <p align="left"> <a href="https://github.com/argilla-io/distilabel"> <img src="https://raw.githubusercontent.com/argilla-io/distilabel/main/docs/assets/distilabel-badge-light.png" alt="Built with Distilabel" width="200" height="32"/> </a> </p> # Dataset Card for my-distiset-8c05c9f2 This dataset has been created with [distilabel](https://distilabel.argilla.io/). ## Dataset Summary This dataset contains a `pipeline.yaml` which can be used to reproduce the pipeline that generated it in distilabel using the `distilabel` CLI: ```console distilabel pipeline run --config "https://huggingface.co/datasets/yasserrmd/my-distiset-8c05c9f2/raw/main/pipeline.yaml" ``` or explore the configuration: ```console distilabel pipeline info --config "https://huggingface.co/datasets/yasserrmd/my-distiset-8c05c9f2/raw/main/pipeline.yaml" ``` ## Dataset structure The examples have the following structure per configuration: <details><summary> Configuration: default </summary><hr> ```json { "label": 0, "text": "It\u0027s okay to leave leftovers at room temperature for up to 2 hours before refrigerating them." } ``` This subset can be loaded as: ```python from datasets import load_dataset ds = load_dataset("yasserrmd/my-distiset-8c05c9f2", "default") ``` Or simply as it follows, since there's only one configuration and is named `default`: ```python from datasets import load_dataset ds = load_dataset("yasserrmd/my-distiset-8c05c9f2") ``` </details>

ErikaaWang/oasst1_highqual_ift

ErikaaWang

2024-12-19T10:30:39Z

44

0

[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2024-12-19T10:30:31Z

0

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train_sft num_bytes: 5024033 num_examples: 3463 - name: test_sft num_bytes: 259338 num_examples: 186 download_size: 3091231 dataset_size: 5283371 configs: - config_name: default data_files: - split: train_sft path: data/train_sft-* - split: test_sft path: data/test_sft-* ---

mahdiR128/fiting_clothes_in_body_2

mahdiR128

2024-11-26T15:05:18Z

15

0

[ "size_categories:n<1K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2024-11-26T15:03:00Z

0

--- dataset_info: features: - name: image dtype: image - name: text dtype: string splits: - name: train num_bytes: 3613862.0 num_examples: 7 download_size: 3614947 dataset_size: 3613862.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

mteb/CUADJointIPOwnershipLegalBenchClassification

mteb

2025-05-06T11:54:36Z

0

[ "task_categories:text-classification", "annotations_creators:expert-annotated", "multilinguality:monolingual", "language:eng", "license:cc-by-4.0", "modality:text", "arxiv:2308.11462", "arxiv:2103.06268", "arxiv:2502.13595", "arxiv:2210.07316", "region:us", "mteb", "text" ]

[ "text-classification" ]

2025-05-06T11:54:32Z

0

--- annotations_creators: - expert-annotated language: - eng license: cc-by-4.0 multilinguality: monolingual task_categories: - text-classification task_ids: [] dataset_info: features: - name: text dtype: string - name: label dtype: int64 splits: - name: train num_bytes: 4431 num_examples: 6 - name: test num_bytes: 74151 num_examples: 192 download_size: 49562 dataset_size: 78582 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* tags: - mteb - text ---  <div align="center" style="padding: 40px 20px; background-color: white; border-radius: 12px; box-shadow: 0 2px 10px rgba(0, 0, 0, 0.05); max-width: 600px; margin: 0 auto;"> <h1 style="font-size: 3.5rem; color: #1a1a1a; margin: 0 0 20px 0; letter-spacing: 2px; font-weight: 700;">CUADJointIPOwnershipLegalBenchClassification</h1> <div style="font-size: 1.5rem; color: #4a4a4a; margin-bottom: 5px; font-weight: 300;">An <a href="https://github.com/embeddings-benchmark/mteb" style="color: #2c5282; font-weight: 600; text-decoration: none;" onmouseover="this.style.textDecoration='underline'" onmouseout="this.style.textDecoration='none'">MTEB</a> dataset</div> <div style="font-size: 0.9rem; color: #2c5282; margin-top: 10px;">Massive Text Embedding Benchmark</div> </div> This task was constructed from the CUAD dataset. It consists of determining if the clause provides for joint or shared ownership of intellectual property between the parties to the contract. | | | |---------------|---------------------------------------------| | Task category | t2c | | Domains | Legal, Written | | Reference | https://huggingface.co/datasets/nguha/legalbench | ## How to evaluate on this task You can evaluate an embedding model on this dataset using the following code: ```python import mteb task = mteb.get_tasks(["CUADJointIPOwnershipLegalBenchClassification"]) evaluator = mteb.MTEB(task) model = mteb.get_model(YOUR_MODEL) evaluator.run(model) ```  To learn more about how to run models on `mteb` task check out the [GitHub repitory](https://github.com/embeddings-benchmark/mteb). ## Citation If you use this dataset, please cite the dataset as well as [mteb](https://github.com/embeddings-benchmark/mteb), as this dataset likely includes additional processing as a part of the [MMTEB Contribution](https://github.com/embeddings-benchmark/mteb/tree/main/docs/mmteb). ```bibtex @misc{guha2023legalbench, archiveprefix = {arXiv}, author = {Neel Guha and Julian Nyarko and Daniel E. Ho and Christopher Ré and Adam Chilton and Aditya Narayana and Alex Chohlas-Wood and Austin Peters and Brandon Waldon and Daniel N. Rockmore and Diego Zambrano and Dmitry Talisman and Enam Hoque and Faiz Surani and Frank Fagan and Galit Sarfaty and Gregory M. Dickinson and Haggai Porat and Jason Hegland and Jessica Wu and Joe Nudell and Joel Niklaus and John Nay and Jonathan H. Choi and Kevin Tobia and Margaret Hagan and Megan Ma and Michael Livermore and Nikon Rasumov-Rahe and Nils Holzenberger and Noam Kolt and Peter Henderson and Sean Rehaag and Sharad Goel and Shang Gao and Spencer Williams and Sunny Gandhi and Tom Zur and Varun Iyer and Zehua Li}, eprint = {2308.11462}, primaryclass = {cs.CL}, title = {LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models}, year = {2023}, } @article{hendrycks2021cuad, author = {Hendrycks, Dan and Burns, Collin and Chen, Anya and Ball, Spencer}, journal = {arXiv preprint arXiv:2103.06268}, title = {Cuad: An expert-annotated nlp dataset for legal contract review}, year = {2021}, } @article{enevoldsen2025mmtebmassivemultilingualtext, title={MMTEB: Massive Multilingual Text Embedding Benchmark}, author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Michail and John Yang and Manuel Faysse and Aleksei Vatolin and Nandan Thakur and Manan Dey and Dipam Vasani and Pranjal Chitale and Simone Tedeschi and Nguyen Tai and Artem Snegirev and Michael Günther and Mengzhou Xia and Weijia Shi and Xing Han Lù and Jordan Clive and Gayatri Krishnakumar and Anna Maksimova and Silvan Wehrli and Maria Tikhonova and Henil Panchal and Aleksandr Abramov and Malte Ostendorff and Zheng Liu and Simon Clematide and Lester James Miranda and Alena Fenogenova and Guangyu Song and Ruqiya Bin Safi and Wen-Ding Li and Alessia Borghini and Federico Cassano and Hongjin Su and Jimmy Lin and Howard Yen and Lasse Hansen and Sara Hooker and Chenghao Xiao and Vaibhav Adlakha and Orion Weller and Siva Reddy and Niklas Muennighoff}, publisher = {arXiv}, journal={arXiv preprint arXiv:2502.13595}, year={2025}, url={https://arxiv.org/abs/2502.13595}, doi = {10.48550/arXiv.2502.13595}, } @article{muennighoff2022mteb, author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Lo{\"\i}c and Reimers, Nils}, title = {MTEB: Massive Text Embedding Benchmark}, publisher = {arXiv}, journal={arXiv preprint arXiv:2210.07316}, year = {2022} url = {https://arxiv.org/abs/2210.07316}, doi = {10.48550/ARXIV.2210.07316}, } ``` # Dataset Statistics <details> <summary> Dataset Statistics</summary> The following code contains the descriptive statistics from the task. These can also be obtained using: ```python import mteb task = mteb.get_task("CUADJointIPOwnershipLegalBenchClassification") desc_stats = task.metadata.descriptive_stats ``` ```json { "test": { "num_samples": 192, "number_of_characters": 71841, "number_texts_intersect_with_train": 0, "min_text_length": 68, "average_text_length": 374.171875, "max_text_length": 1415, "unique_text": 192, "unique_labels": 2, "labels": { "1": { "count": 96 }, "0": { "count": 96 } } }, "train": { "num_samples": 6, "number_of_characters": 4359, "number_texts_intersect_with_train": null, "min_text_length": 190, "average_text_length": 726.5, "max_text_length": 1761, "unique_text": 6, "unique_labels": 2, "labels": { "1": { "count": 3 }, "0": { "count": 3 } } } } ``` </details> --- *This dataset card was automatically generated using [MTEB](https://github.com/embeddings-benchmark/mteb)*

weepcat/summarization_partial_reward_model_random_length-1

weepcat

2025-01-21T10:40:04Z

17

0

[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-01-21T10:38:24Z

0

--- dataset_info: features: - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: prompt dtype: string splits: - name: train num_bytes: 1812682139.0 num_examples: 603820 - name: test num_bytes: 1629397885.0 num_examples: 543822 download_size: 735029273 dataset_size: 3442080024.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

robinsmits/ChatAlpaca-20K

robinsmits

2024-01-08T22:18:52Z

64

4

[ "task_categories:text-generation", "language:en", "license:apache-2.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us", "chat", "alpaca", "gpt-3.5" ]

[ "conversational", "text-generation" ]

2024-01-06T13:44:38Z

1

--- language: - en license: apache-2.0 size_categories: - 10K<n<100K task_categories: - conversational - text-generation pretty_name: ChatAlpaca 20K tags: - chat - alpaca - gpt-3.5 dataset_info: features: - name: id dtype: int32 - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: original num_bytes: 68350442 num_examples: 20000 - name: train num_bytes: 66983433.16 num_examples: 19600 - name: test num_bytes: 1367008.84 num_examples: 400 download_size: 69122205 dataset_size: 136700884.0 configs: - config_name: default data_files: - split: original path: data/original-* - split: train path: data/train-* - split: test path: data/test-* --- # Dataset Card for ChatAlpaca 20K ## ChatAlpaca: A Multi-Turn Dialogue Corpus based on Alpaca Instructions ### Dataset Description ChatAlpaca is a chat dataset that aims to help researchers develop models for instruction-following in multi-turn conversations. The dataset is an extension of the [Stanford Alpaca data](https://github.com/tatsu-lab/stanford_alpaca), which contains multi-turn instructions and their corresponding responses. ChatAlpaca is developed by Chinese Information Processing Laboratory at the Institute of Software, Chinese Academy of Sciences (www.icip.org.cn). In this dataset, we use ChatGPT (GPT-3.5-turbo) to generate follow-up utterances and continue the conversation with ChatGPT. This process results in multi-turn conversations where the simulated user provides instructions and ChatGPT responds accordingly. ### Dataset Structure The data in this repository consists of a JSON file chatalpaca-20k.json containing the multi-turn instruction-following conversations. Each item in the data file represents a different conversation between a simulated user and the ChatGPT. The data currently contains a total of 20,000 conversations. I've created 3 splits in the dataset: * original: all the data as available in the original chatalpaca-20k.json * train: 19600 rows for training * test: 400 rows for testing or validating. * The conversations in the dataset begin with an instruction, followed by a response from ChatGPT, which are from the Stanford Alpaca data. The conversation then continues with the user providing further instructions and ChatGPT responding accordingly. Each item in the dataset is a list of dictionaries, each dictionary contains the following fields: * id: int, identifier * messages: list, contains multiple dictionaries representing the conversations Each dictionary in the messages list contains the following fields: * role: str, with values "user" or "assistant"; * content: str, the conversation content. ! Note: In the original .json file the researchers used different field and variable names. I've renamed them to be consistent with the defacto standard as used for chat conversations. Here is an example of one conversation: ``` [ { "role": "user", "content": "Identify the odd one out: Twitter, Instagram, Telegram" }, { "role": "assistant", "content": "Telegram" }, { "role": "user", "content": "What makes Telegram different from Twitter and Instagram?" }, { "role": "assistant", "content": "Telegram is a cloud-based instant messaging app that focuses on privacy and security. Unlike Twitter and Instagram which are mainly used for following news, celebrities, and sharing images, Telegram was created as a secure messaging app for private and group communication. Telegram also offers more advanced features than Twitter and Instagram, such as the ability to schedule messages, create bots, and send encrypted messages." }, { "role": "user", "content": "Can you give me an example of how the scheduling messages feature can be useful on Telegram?" }, { "role": "assistant", "content": "Sure! The scheduling messages feature on Telegram can be useful in many different situations. Here's an example:\n\nLet's say you have a workgroup on Telegram, and you want to send a message to everyone in the group to remind them of a meeting. However, you know that most of the people in the group are busy at work during the time you want to send the message.\n\nThat's where the scheduling messages feature comes in. You can schedule the message to be sent at a later time when people are more likely to be free, such as during their lunch break or after work. This way, everyone in the group will receive the message at the same time, and you won't have to worry about anyone missing the important reminder.\n\nOverall, the scheduling messages feature can be really helpful for coordinating communication with groups of people on Telegram, whether it's for work, social events, or anything else." }, { "role": "user", "content": "Goodbye." } ] ``` ### Discussion of Biases As this dataset contains machine-generated texts it could contain potential biases. Verify and validate this for your specific usage scenario. ## Citation !! Note. I've only put this dataset on HuggingFace since it was not available. All credits go to the original researchers and creators. Please cite the original repository if you use the dataset. ``` @misc{ChatAlpaca, author = {Ning Bian and Hongyu Lin and Yaojie Lu and Xianpei Han and Le Sun and Ben He }, title = {ChatAlpaca: A Multi-Turn Dialogue Corpus based on Alpaca Instructions}, year = {2023}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/cascip/ChatAlpaca}}, } ```

sumuks/LaMP-AmazonProductReviews-4.25M

sumuks

2025-06-02T23:52:31Z

0

[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2024-07-26T16:02:34Z

0

--- dataset_info: features: - name: review_id dtype: string - name: review dtype: string - name: score dtype: string - name: profile_id dtype: string - name: total_profile_review_count dtype: int64 splits: - name: train num_bytes: 3397618326 num_examples: 4250311 download_size: 1908683064 dataset_size: 3397618326 configs: - config_name: default data_files: - split: train path: data/train-* ---

ToviTu/tebase-abstract-qa-grounded

ToviTu

2025-05-06T20:15:29Z

27

0

[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-05-01T18:06:20Z

0

--- dataset_info: features: - name: question dtype: string - name: answer dtype: string - name: abstract dtype: string - name: retrieved_contexts sequence: string - name: option_A dtype: string - name: option_B dtype: string - name: option_C dtype: string - name: option_D dtype: string splits: - name: train num_bytes: 46722 num_examples: 10 - name: test num_bytes: 5262289 num_examples: 990 download_size: 2806050 dataset_size: 5309011 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

JoveMiracle/cf_router_clean4k-6k

JoveMiracle

2025-03-28T20:31:38Z

17

0

[ "size_categories:1K<n<10K", "format:parquet", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-03-28T20:31:31Z

0

--- dataset_info: features: - name: embeddings sequence: float32 splits: - name: train num_bytes: 24585852 num_examples: 3999 download_size: 26925936 dataset_size: 24585852 configs: - config_name: default data_files: - split: train path: data/train-* ---

mteb/SNLHierarchicalClusteringP2P

mteb

2025-06-15T17:29:10Z

0

[ "task_categories:text-classification", "annotations_creators:derived", "multilinguality:monolingual", "language:nob", "license:cc-by-nc-4.0", "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2502.13595", "arxiv:2210.07316", "region:us", "mteb", "text" ]

[ "text-classification" ]

2025-06-15T17:28:27Z

0

--- annotations_creators: - derived language: - nob license: cc-by-nc-4.0 multilinguality: monolingual task_categories: - text-classification task_ids: [] tags: - mteb - text dataset_info: features: - name: sentences dtype: string - name: labels sequence: string splits: - name: train num_bytes: 22764276 num_examples: 10874 - name: validation num_bytes: 1612730 num_examples: 819 - name: test num_bytes: 2747385 num_examples: 1300 download_size: 16642874 dataset_size: 27124391 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* ---  <div align="center" style="padding: 40px 20px; background-color: white; border-radius: 12px; box-shadow: 0 2px 10px rgba(0, 0, 0, 0.05); max-width: 600px; margin: 0 auto;"> <h1 style="font-size: 3.5rem; color: #1a1a1a; margin: 0 0 20px 0; letter-spacing: 2px; font-weight: 700;">SNLHierarchicalClusteringP2P</h1> <div style="font-size: 1.5rem; color: #4a4a4a; margin-bottom: 5px; font-weight: 300;">An <a href="https://github.com/embeddings-benchmark/mteb" style="color: #2c5282; font-weight: 600; text-decoration: none;" onmouseover="this.style.textDecoration='underline'" onmouseout="this.style.textDecoration='none'">MTEB</a> dataset</div> <div style="font-size: 0.9rem; color: #2c5282; margin-top: 10px;">Massive Text Embedding Benchmark</div> </div> Webscrabed articles from the Norwegian lexicon 'Det Store Norske Leksikon'. Uses articles categories as clusters. | | | |---------------|---------------------------------------------| | Task category | t2c | | Domains | Encyclopaedic, Non-fiction, Written | | Reference | https://huggingface.co/datasets/adrlau/navjordj-SNL_summarization_copy | ## How to evaluate on this task You can evaluate an embedding model on this dataset using the following code: ```python import mteb task = mteb.get_task("SNLHierarchicalClusteringP2P") evaluator = mteb.MTEB([task]) model = mteb.get_model(YOUR_MODEL) evaluator.run(model) ```  To learn more about how to run models on `mteb` task check out the [GitHub repository](https://github.com/embeddings-benchmark/mteb). ## Citation If you use this dataset, please cite the dataset as well as [mteb](https://github.com/embeddings-benchmark/mteb), as this dataset likely includes additional processing as a part of the [MMTEB Contribution](https://github.com/embeddings-benchmark/mteb/tree/main/docs/mmteb). ```bibtex @mastersthesis{navjord2023beyond, author = {Navjord, J{\\o}rgen Johnsen and Korsvik, Jon-Mikkel Ryen}, school = {Norwegian University of Life Sciences, {\\AA}s}, title = {Beyond extractive: advancing abstractive automatic text summarization in Norwegian with transformers}, year = {2023}, } @article{enevoldsen2025mmtebmassivemultilingualtext, title={MMTEB: Massive Multilingual Text Embedding Benchmark}, author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Michail and John Yang and Manuel Faysse and Aleksei Vatolin and Nandan Thakur and Manan Dey and Dipam Vasani and Pranjal Chitale and Simone Tedeschi and Nguyen Tai and Artem Snegirev and Michael Günther and Mengzhou Xia and Weijia Shi and Xing Han Lù and Jordan Clive and Gayatri Krishnakumar and Anna Maksimova and Silvan Wehrli and Maria Tikhonova and Henil Panchal and Aleksandr Abramov and Malte Ostendorff and Zheng Liu and Simon Clematide and Lester James Miranda and Alena Fenogenova and Guangyu Song and Ruqiya Bin Safi and Wen-Ding Li and Alessia Borghini and Federico Cassano and Hongjin Su and Jimmy Lin and Howard Yen and Lasse Hansen and Sara Hooker and Chenghao Xiao and Vaibhav Adlakha and Orion Weller and Siva Reddy and Niklas Muennighoff}, publisher = {arXiv}, journal={arXiv preprint arXiv:2502.13595}, year={2025}, url={https://arxiv.org/abs/2502.13595}, doi = {10.48550/arXiv.2502.13595}, } @article{muennighoff2022mteb, author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Loïc and Reimers, Nils}, title = {MTEB: Massive Text Embedding Benchmark}, publisher = {arXiv}, journal={arXiv preprint arXiv:2210.07316}, year = {2022} url = {https://arxiv.org/abs/2210.07316}, doi = {10.48550/ARXIV.2210.07316}, } ``` # Dataset Statistics <details> <summary> Dataset Statistics</summary> The following code contains the descriptive statistics from the task. These can also be obtained using: ```python import mteb task = mteb.get_task("SNLHierarchicalClusteringP2P") desc_stats = task.metadata.descriptive_stats ``` ```json { "test": { "num_samples": 1300, "number_of_characters": 2583029, "min_text_length": 400, "average_text_length": 1986.9453846153847, "max_text_length": 68710, "unique_texts": 968, "min_labels_per_text": 1, "average_labels_per_text": 4.136153846153846, "max_labels_per_text": 201, "unique_labels": 1246, "labels": { "Realfag": { "count": 89 }, "Fysikk": { "count": 32 }, "Varme- og stoffl\u00e6re": { "count": 3 }, "Spr\u00e5k og litteratur": { "count": 139 }, "Spr\u00e5kvitenskapens fagdisipliner": { "count": 20 }, "Pragmatikk": { "count": 1 }, "Onomastikk": { "count": 14 }, "Personnavn": { "count": 14 }, "Fornavn": { "count": 14 }, "Guttenavn": { "count": 9 }, "Kunst og estetikk": { "count": 201 }, "Metall- og smykkekunst": { "count": 1 }, "Biologi": { "count": 92 }, "Vitenskapsgrener i biologien": { "count": 24 }, "Botanikk": { "count": 8 }, "Planteanatomi": { "count": 5 }, "Plantenes vevsystemer": { "count": 1 }, "Andre vev hos planter": { "count": 1 }, "Teknologi og industri": { "count": 97 }, "Transport": { "count": 35 }, "Navigasjon": { "count": 2 }, "Kjemi": { "count": 28 }, "Polymerkjemi": { "count": 3 }, "Sport og spill": { "count": 28 }, "Ballsport": { "count": 15 }, "Biljard": { "count": 2 }, "S\u00f8m": { "count": 8 }, " kl\u00e6r og mote": { "count": 8 }, "Sko": { "count": 1 }, "Veterin\u00e6rmedisin": { "count": 2 }, "Fiskehelse": { "count": 2 }, "Fotball": { "count": 9 }, "Norsk fotball": { "count": 4 }, "Musikk": { "count": 69 }, "Klassisk musikk": { "count": 25 }, "Den klassiske musikkens historie": { "count": 12 }, "Klassisk musikk f\u00f8r 1600": { "count": 1 }, "M\u00e5l og vekt": { "count": 7 }, "Eldre m\u00e5leenheter": { "count": 1 }, "Historie": { "count": 192 }, "Kulturhistorie": { "count": 6 }, "Folkelige skikker og tradisjoner": { "count": 2 }, "Spill": { "count": 3 }, "Brettspill": { "count": 2 }, "Biokjemi": { "count": 1 }, "Aminosyrer": { "count": 1 }, "Geografi": { "count": 178 }, "Norges geografi": { "count": 45 }, "Agder": { "count": 4 }, "Lindesnes": { "count": 1 }, "Verdens geografi": { "count": 128 }, "Afrika": { "count": 26 }, "Kapp Verdes geografi": { "count": 1 }, "Viken": { "count": 9 }, "Halden": { "count": 1 }, "Samfunn": { "count": 97 }, "Samfunnsfag": { "count": 26 }, "Statsvitenskap": { "count": 7 }, "Valgforskning og sammenliknende politikk": { "count": 1 }, "Politiske begreper": { "count": 1 }, "Planteriket": { "count": 24 }, "Dekkfr\u00f8ete planter": { "count": 24 }, "Enfr\u00f8bladete planter": { "count": 2 }, "Aspargesordenen": { "count": 1 }, "Orkid\u00e9familien": { "count": 1 }, "Marihandslekta": { "count": 1 }, "Jus": { "count": 34 }, "Formuerett": { "count": 8 }, "Selskapsrett": { "count": 5 }, "Telekommunikasjon og kringkasting": { "count": 2 }, "Kommunikasjonsteknologi": { "count": 2 }, "Oseania": { "count": 6 }, "Australias geografi": { "count": 2 }, "Jernbane og sporvei": { "count": 1 }, "Jernbanebiografier": { "count": 1 }, "Verdens historie og samtidshistorie": { "count": 126 }, "Europa": { "count": 192 }, "Den greske antikken": { "count": 6 }, "Sj\u00f8fart og skipsindustri": { "count": 16 }, "Fyrvesen og losvesen": { "count": 5 }, "Fyrvesen": { "count": 4 }, "Norske fyr": { "count": 4 }, "Norsk og nordisk historie": { "count": 26 }, "Norges historie": { "count": 20 }, "Norges historie fra 1945 til 1970": { "count": 1 }, "Nord- og Mellom-Amerika": { "count": 24 }, "Honduras\u2019 geografi": { "count": 1 }, "Historiske hjelpevitenskaper": { "count": 18 }, "Slektsforskning og genealogi": { "count": 17 }, "Utenlandske slekter": { "count": 7 }, "Folkegrupper i Nord- og Mellom-Amerika": { "count": 3 }, "Folkegrupper i Nord-Amerika": { "count": 3 }, "Litteratur i verden": { "count": 88 }, "Nord- og Mellom-Amerikas litteratur": { "count": 11 }, "USAs litteratur": { "count": 7 }, "USAs litteratur p\u00e5 1600 og 1700-tallet": { "count": 1 }, "Religion og filosofi": { "count": 95 }, "Religioner og livssyn": { "count": 61 }, "Kristendom": { "count": 48 }, "Det gamle testamentet": { "count": 2 }, "Personer i Det gamle testamentet": { "count": 2 }, "Tofr\u00f8bladete planter": { "count": 21 }, "Vierordenen": { "count": 3 }, "Vierfamilien": { "count": 1 }, "Vierslekta": { "count": 1 }, "Afrikas litteratur": { "count": 2 }, "Elfenbenskystens litteratur": { "count": 1 }, "N\u00e6ringsmidler og husholdning": { "count": 13 }, "Mat": { "count": 7 }, "Ulike lands kj\u00f8kken": { "count": 2 }, "S\u00f8r-Europas kj\u00f8kken": { "count": 1 }, "Italiensk mat": { "count": 1 }, "Klassisk musikk 1900\u20131950": { "count": 3 }, "Norske klassiske komponister og verker 1900\u20131950": { "count": 1 }, "Atferdsbiologi": { "count": 1 }, "Skip og skipstyper": { "count": 5 }, "Seilskip": { "count": 2 }, "Demografi": { "count": 2 }, "Filosofiens fagdisipliner": { "count": 12 }, "Filosofisk logikk": { "count": 1 }, "Historiske b\u00e5ttyper": { "count": 2 }, "Vikingskip": { "count": 1 }, "Bildende kunst": { "count": 49 }, "Kunstvitenskap": { "count": 5 }, "Termer og begreper i bildende kunst": { "count": 4 }, "Rubladordenen": { "count": 3 }, "Rubladfamilien": { "count": 3 }, "\u00c5kersteinfr\u00f8slekta": { "count": 1 }, "Familierett": { "count": 3 }, "Oslo": { "count": 1 }, "Atom- og kjernefysikk": { "count": 3 }, "Teknologi": { "count": 2 }, "Sjakk": { "count": 1 }, "Frankrikes historie": { "count": 11 }, "Frankrikes samtidshistorie": { "count": 3 }, "Italias geografi": { "count": 4 }, "Storbritannia og Nord-Irlands geografi": { "count": 13 }, "Katolisisme": { "count": 8 }, "Klostervesenet": { "count": 4 }, "Verdens historie": { "count": 5 }, "Den kalde krigen": { "count": 2 }, "Cellens organeller og mikrostruktur": { "count": 1 }, "Vekst og vekstanlegg": { "count": 1 }, "Analytisk kjemi": { "count": 2 }, "Spektroskopi": { "count": 2 }, "Grammatikk": { "count": 2 }, "Morfologi": { "count": 2 }, "Finlands litteratur": { "count": 4 }, "Utdanning og forskning": { "count": 12 }, "Pedagogikk": { "count": 3 }, "Biografier innen pedagogisk teori": { "count": 2 }, "Frankrikes litteratur": { "count": 14 }, "Frankrikes litteratur p\u00e5 1700-tallet": { "count": 2 }, "Psykologi": { "count": 4 }, "Personlighetspsykologi": { "count": 3 }, "Musikkbransje": { "count": 1 }, "Plateselskaper": { "count": 1 }, "Romanias historie": { "count": 3 }, "IT": { "count": 4 }, "Internett": { "count": 2 }, "Antigua og Barbudas geografi": { "count": 1 }, "Norges historie fra 1660 til 1814": { "count": 3 }, "Nordland": { "count": 6 }, "Bindal": { "count": 1 }, "Storbritannia og Nord-Irlands historie": { "count": 7 }, "Italias litteratur": { "count": 4 }, "Italias litteratur p\u00e5 1500-tallet": { "count": 2 }, "Arbeid og velferd": { "count": 4 }, "Arbeidsliv": { "count": 2 }, "Arbeidslivsorganisasjoner": { "count": 1 }, "Europas geografi generelt": { "count": 2 }, "Internasjonale dirigenter": { "count": 3 }, "Popul\u00e6rmusikk": { "count": 20 }, "Pop og rock": { "count": 11 }, "Internasjonal pop og rock": { "count": 10 }, "Afrikas historie": { "count": 2 }, "USAs historie": { "count": 5 }, "USAs historie fra 1960": { "count": 2 }, "Skipstyper": { "count": 1 }, "De ortodokse kirker": { "count": 2 }, "Sveriges litteratur": { "count": 5 }, "Sveriges litteratur 1900-1960": { "count": 2 }, "Avtalerett": { "count": 2 }, "Jentenavn": { "count": 5 }, "Energi": { "count": 6 }, "Belysning": { "count": 2 }, "Asia": { "count": 44 }, "Indias geografi": { "count": 3 }, "Br\u00f8nn\u00f8y": { "count": 1 }, "Anatomi": { "count": 3 }, "Insektenes anatomi og fysiologi": { "count": 1 }, "Pakistans geografi": { "count": 2 }, "Historiske religioner": { "count": 8 }, "Gresk religion": { "count": 2 }, "\u00d8konomi og n\u00e6ringsliv": { "count": 25 }, "N\u00e6ringsliv": { "count": 10 }, "Bedrifter og personer": { "count": 9 }, "Bedrifter i internasjonal n\u00e6ringslivshistorie": { "count": 2 }, "Politikk og offentlig forvaltning": { "count": 12 }, "Norsk politikk og offentlig forvaltning": { "count": 9 }, "Partier og politikere": { "count": 7 }, "Norske politikere": { "count": 7 }, "Tidligere politikere": { "count": 5 }, "Belarus\u2019 geografi": { "count": 1 }, "Matematikk": { "count": 6 }, "Sannsynlighet og statistikk": { "count": 2 }, "Statistikk": { "count": 2 }, "Film": { "count": 23 }, " TV og teater": { "count": 23 }, "Film og TV": { "count": 18 }, "Norske filmer og TV-serier": { "count": 1 }, "Arkitektur og landskap": { "count": 29 }, "Arkitekturhistorie": { "count": 9 }, "Islamsk arkitekturhistorie": { "count": 2 }, "Organisk kjemi": { "count": 7 }, "Organiske forbindelser": { "count": 7 }, "Historievitenskap": { "count": 8 }, "Historikere": { "count": 4 }, "Storbritannia og Nord-Irlands litteratur": { "count": 8 }, "Storbritannia og Nord-Irlands litteratur p\u00e5 1900-tallet": { "count": 3 }, "Folkegrupper i Afrika": { "count": 3 }, "Spr\u00e5kvitenskapens grunnbegreper": { "count": 1 }, "Luftfart": { "count": 6 }, "Luftfart\u00f8y": { "count": 1 }, "Sivilflytyper": { "count": 1 }, "Passasjerfly": { "count": 1 }, "Bygg og anlegg": { "count": 6 }, "Betong": { "count": 2 }, " sement og m\u00f8rtel": { "count": 2 }, "S\u00f8r-Amerikas geografi": { "count": 9 }, "Argentinas geografi": { "count": 2 }, "Bosnia-Hercegovinas geografi": { "count": 2 }, "Folkemusikk": { "count": 1 }, "Kristendommens historie": { "count": 6 }, "Tidlig kristendom": { "count": 4 }, "Den norske kirke": { "count": 5 }, "Buddhisme": { "count": 2 }, "Nyreligi\u00f8sitet": { "count": 2 }, "\u00d8stlig innflytelse": { "count": 1 }, "Medier": { "count": 17 }, "Forlagsdrift": { "count": 1 }, "Amt og len i Norge": { "count": 1 }, "Oster": { "count": 3 }, "Tekstiler": { "count": 4 }, "Flyteknikk": { "count": 1 }, "Flygeteori": { "count": 1 }, "Kirker": { "count": 7 }, " slott og g\u00e5rder": { "count": 7 }, "Slott og palasser": { "count": 3 }, "Klassisk musikk i barokken": { "count": 4 }, "Storbritannia og Nord-Irlands litteratur p\u00e5 1700-tallet": { "count": 3 }, "Drikke": { "count": 3 }, "Vin": { "count": 2 }, "Vinterminologi": { "count": 1 }, "Jazz": { "count": 17 }, "Nord-Amerikanske jazzut\u00f8vere og -ensembler": { "count": 10 }, " 1920 \u2013 1960": { "count": 2 }, "Danmarks geografi": { "count": 5 }, "Filippinenes geografi": { "count": 1 }, "Sj\u00f8merker": { "count": 1 }, "Elektrokjemi og metallurgi": { "count": 3 }, "Legeringer": { "count": 1 }, "St\u00e5l og andre jernlegeringer": { "count": 1 }, "Penger": { "count": 4 }, "Numismatikk": { "count": 2 }, "Taiwans geografi": { "count": 1 }, "Burkina Fasos geografi": { "count": 3 }, "Blues": { "count": 2 }, "Internasjonale bluesmusikere": { "count": 2 }, "Journalistikk": { "count": 2 }, "Journalistiske begreper": { "count": 2 }, "Middelalderens arkitekturhistorie": { "count": 4 }, "Frankrikes geografi": { "count": 8 }, "Jazzens historie": { "count": 1 }, "Tysk-romerske rike": { "count": 1 }, "Biografier i Det tysk-romerske riket": { "count": 1 }, "Geometri og topologi": { "count": 3 }, "Algebraisk geometri": { "count": 3 }, "USAs geografi": { "count": 7 }, "Delstater og omr\u00e5der i USA": { "count": 1 }, "Meteorologi": { "count": 2 }, "Klima": { "count": 1 }, "Klima i Norge": { "count": 1 }, "Norske tradisjonsb\u00e5ter": { "count": 1 }, "Nordnorske tradisjonsb\u00e5ter": { "count": 1 }, "Politi og kriminalitet": { "count": 4 }, "Politivesen": { "count": 2 }, "Politifaglige begreper": { "count": 2 }, "Kulturinstitusjoner": { "count": 6 }, "Museum": { "count": 3 }, "Filosofiens historie": { "count": 9 }, "Middelalderens og renessansens filosofi": { "count": 4 }, "Forsvar og sikkerhet": { "count": 18 }, "Forsvar i verden": { "count": 3 }, "Bokkunst og skrift": { "count": 2 }, "Skriftdesign og typografi": { "count": 1 }, "Typografer og skriftdesignere": { "count": 1 }, "Frankrikes nyere litteratur": { "count": 3 }, "Romerrikets litteratur": { "count": 2 }, "Verk i Romerrikets litteratur": { "count": 1 }, "Dyreriket": { "count": 30 }, "Ryggstrengdyr": { "count": 23 }, "Virveldyr": { "count": 26 }, "Fugler": { "count": 8 }, "Dykkere": { "count": 1 }, "Monarki": { "count": 1 }, "Maskiner": { "count": 10 }, "Maskinelementer": { "count": 1 }, "Jus generelt": { "count": 2 }, "Petroleum": { "count": 6 }, "Petroleumsutvinning": { "count": 4 }, "Boreteknologi": { "count": 1 }, "Landbruk": { "count": 8 }, "Husdyr": { "count": 7 }, "Hund": { "count": 5 }, "Hunderaser": { "count": 5 }, "Offentlig politikk og administrasjon": { "count": 3 }, "Politisk og \u00f8konomisk filosofi": { "count": 5 }, "Internasjonal tekstilindustri": { "count": 1 }, "Spanias geografi": { "count": 6 }, "Multippelenheter i SI-systemet": { "count": 1 }, " 1980 til i dag": { "count": 7 }, "Salmesang": { "count": 2 }, "Milit\u00e6re biografier": { "count": 4 }, "Norske milit\u00e6re biografier": { "count": 2 }, "Kristne trossamfunn": { "count": 9 }, "Spr\u00e5kforskere": { "count": 2 }, "Norske spr\u00e5kforskere og spr\u00e5kfolk": { "count": 1 }, "Romerrikets historie": { "count": 10 }, "Filmteknikk": { "count": 2 }, "Europeisk film og TV": { "count": 6 }, "Europeiske filmer og tv-serier": { "count": 1 }, "Bil": { "count": 8 }, "Bilfag": { "count": 4 }, "Bilens sikkerhetssystemer": { "count": 2 }, "Bygningstyper": { "count": 2 }, "Norges historie fra 1814 til 1884": { "count": 2 }, "Europeiske jazzut\u00f8vere og -ensembler": { "count": 2 }, " 1920 \u2013 1980": { "count": 4 }, "S\u00f8r-Amerika": { "count": 7 }, "Bolivias historie": { "count": 2 }, "Internasjonalt milit\u00e6rt samarbeid": { "count": 2 }, "Internasjonale milit\u00e6re organisasjoner": { "count": 2 }, "NATO": { "count": 2 }, "Kristen teologi og trosl\u00e6re": { "count": 2 }, "Leddyr": { "count": 4 }, "Insekter": { "count": 4 }, "Tovinger": { "count": 1 }, "Gallmygg": { "count": 1 }, "Dasineura": { "count": 1 }, "Mauritius\u2019 historie": { "count": 1 }, "Mauritius\u2019 samtidshistorie": { "count": 1 }, "Historiske riker i Sentral-Afrika": { "count": 1 }, "Politikkomr\u00e5der": { "count": 2 }, "Milj\u00f8vern": { "count": 1 }, "Milj\u00f8bevegelsen": { "count": 1 }, "Programmering": { "count": 1 }, "Polens historie": { "count": 1 }, "Fotografi": { "count": 2 }, "Fotohistoriske biografier": { "count": 1 }, "Skipstekniske og nautiske begrep": { "count": 5 }, "Immaterialrett": { "count": 1 }, "Opphavsrett": { "count": 1 }, "Kontormaskiner": { "count": 1 }, "Sosiologi": { "count": 6 }, "Sosiologer": { "count": 1 }, "Plantenes form": { "count": 3 }, "Fr\u00f8 og formeringsorganer": { "count": 1 }, "Genealoger": { "count": 1 }, "Storbritannias samtidshistorie": { "count": 1 }, "Samtidskunst": { "count": 10 }, "Skulptur og mosaikk i samtidskunsten": { "count": 4 }, "Bolig og eiendom": { "count": 3 }, "Volleyball": { "count": 1 }, "V\u00e6r": { "count": 1 }, "Skyer og nedb\u00f8r": { "count": 1 }, "Bangladesh' historie": { "count": 1 }, "Bangladesh' samtidshistorie": { "count": 1 }, "Spurvefugler": { "count": 2 }, "Kinas geografi": { "count": 1 }, "V\u00e5pen og milit\u00e6rt materiell": { "count": 3 }, "Marinefart\u00f8y": { "count": 1 }, "Undervannsb\u00e5ter": { "count": 1 }, "Belgias franskspr\u00e5klige litteratur": { "count": 4 }, "Motorkj\u00f8ret\u00f8yer": { "count": 1 }, "Israels historie": { "count": 1 }, "Astronomi": { "count": 17 }, "Solsystemet": { "count": 2 }, "Colombias geografi": { "count": 2 }, "Norges historie fra 1050 til 1300": { "count": 3 }, "\u00d8vrig vintersport": { "count": 2 }, "Skiskyting": { "count": 1 }, "Vestland": { "count": 8 }, "B\u00f8mlo": { "count": 1 }, "Moderne okkultisme": { "count": 1 }, "Frankrikes litteratur p\u00e5 1800-tallet": { "count": 3 }, "Antropologi": { "count": 6 }, "Antropologer": { "count": 3 }, "Musikkteori": { "count": 2 }, "Tonalitet": { "count": 1 }, "Internasjonale bedrifter og varemerker": { "count": 4 }, "Religionsvitenskap": { "count": 6 }, "Spr\u00e5ktypologi": { "count": 1 }, "Ungarns historie": { "count": 2 }, "Vade-": { "count": 2 }, " m\u00e5ke- og alkefugler": { "count": 2 }, "Oseanias litteratur": { "count": 3 }, "New Zealands litteratur": { "count": 1 }, "Pattedyr": { "count": 10 }, "Spissmusdyr": { "count": 1 }, "Spissmusfamilien": { "count": 1 }, "Soricinae": { "count": 1 }, "Soricini": { "count": 1 }, "Sorex": { "count": 1 }, "Fysikalsk kjemi": { "count": 1 }, "Litteraturvitenskap": { "count": 7 }, "Litteraturforskere og kritikere": { "count": 3 }, "Aserbajdsjans historie": { "count": 1 }, "Rettssosiologi": { "count": 1 }, "Chiles geografi": { "count": 1 }, "Norske bedrifter og varemerker": { "count": 3 }, "Klassisk musikk p\u00e5 1800-tallet": { "count": 4 }, "Internasjonale klassiske komponister og verker p\u00e5 1800-tallet": { "count": 3 }, "Flyindustri": { "count": 4 }, "Flyselskaper": { "count": 2 }, "Racketsport": { "count": 2 }, "Tennis": { "count": 2 }, "Prosessmetallurgi": { "count": 1 }, "Tysklands litteratur": { "count": 6 }, "Tysklands litteratur 1900-1950": { "count": 1 }, "Norske klassiske instrumentalister": { "count": 2 }, "Innlandet": { "count": 2 }, "Eidskog": { "count": 1 }, "Nord-amerikansk film og TV": { "count": 7 }, "Nord-amerikanske skuespillere": { "count": 5 }, "Internasjonal politikk": { "count": 2 }, "Troms og Finnmark": { "count": 3 }, "Bardu": { "count": 1 }, "Hinduisme": { "count": 3 }, "Aust-Agder": { "count": 1 }, "Kirkemusikk": { "count": 1 }, "Australias litteratur": { "count": 2 }, "Kunsthistorie": { "count": 31 }, "Ekspresjonisme og fauvisme": { "count": 1 }, "Vannforsyning": { "count": 1 }, "\u00d8vrige sporter": { "count": 2 }, "\u00d8vrig konkurranseidrett": { "count": 1 }, "Norsk pop og rock": { "count": 1 }, "Frankrikes litteratur p\u00e5 1600-tallet": { "count": 1 }, "Arkitekter og arkitektur-institusjoner": { "count": 10 }, "Internasjonale arkitekter fra 1600 til 1900": { "count": 2 }, "Dyrenes anatomi": { "count": 1 }, "Bangladesh' geografi": { "count": 3 }, "Benins historie": { "count": 1 }, "Benins samtidshistorie": { "count": 1 }, "Elektromagnetisme": { "count": 4 }, "Neo-ekspresjonisme og figurativ billedkunst etter 1945": { "count": 4 }, "N\u00e6ringsmiddelteknologi": { "count": 2 }, "Tr\u00f8ndelag": { "count": 3 }, "Skaun": { "count": 1 }, "Sigdal": { "count": 1 }, "Tysklands historie": { "count": 4 }, "Tysklands historie fra 1933 til 1945": { "count": 1 }, "Spr\u00e5kfilosofi": { "count": 1 }, "Kjerneenergi": { "count": 1 }, "Kjernekraftverk": { "count": 1 }, "Reiseliv": { "count": 3 }, "Bedrifter og organisasjoner i internasjonalt reiseliv": { "count": 2 }, "Norske dirigenter": { "count": 1 }, "Soppriket": { "count": 10 }, "Stilksporesopper": { "count": 9 }, "Hymeniesopper": { "count": 7 }, "Ekte hymeniesopper": { "count": 7 }, "Agaricomycetidae": { "count": 5 }, "Skivesoppordenen": { "count": 5 }, "Tricholomataceae": { "count": 1 }, "Ridderhatter": { "count": 1 }, "Indonesias geografi": { "count": 4 }, "Forskningsmetode": { "count": 5 }, "Frankrikes litteratur p\u00e5 1900-tallet": { "count": 4 }, "Aviser": { "count": 9 }, "Avisredakt\u00f8rer": { "count": 2 }, "Portugals litteratur": { "count": 1 }, "Utdanningshistorie": { "count": 1 }, "Pumper og turbiner": { "count": 3 }, "Byer i USA": { "count": 4 }, "USA-assosierte stater og territorer i Oseania": { "count": 1 }, "Korsblomstordenen": { "count": 3 }, "Korsblomstfamilien": { "count": 3 }, "Rublomslekta": { "count": 1 }, "Lyngordenen": { "count": 1 }, "Lyngfamilien": { "count": 1 }, "B\u00e6rlyngslekta": { "count": 1 }, " 1960 \u2013 1980": { "count": 1 }, "Geologi": { "count": 11 }, "Bergarter": { "count": 3 }, "Metamorfe bergarter": { "count": 1 }, "Nederlandsk og flamsk billedkunst 1400-1750": { "count": 2 }, "Kristen misjonsvirksomhet": { "count": 6 }, "Benins geografi": { "count": 1 }, "Romanias geografi": { "count": 2 }, "Molekyl\u00e6rbiologi": { "count": 1 }, "Metoder i celle- og molekyl\u00e6rbiologien": { "count": 1 }, "Skrinneblomslekta": { "count": 1 }, "Norsk bildende kunst fra 1800-1945": { "count": 3 }, "Englands historie": { "count": 1 }, "Kinas historie": { "count": 1 }, "Republikken Kinas historie (1912\u20131949)": { "count": 1 }, "Bunad": { "count": 1 }, " kofter og folkedrakt": { "count": 1 }, "Islam": { "count": 3 }, "Retninger i islam": { "count": 3 }, "Postimpresjonisme": { "count": 2 }, " symbolisme og art nouveau": { "count": 2 }, "Dyrevern": { "count": 1 }, "Tidsregning": { "count": 2 }, "Temabasert reiseliv": { "count": 1 }, "Turisthytter": { "count": 1 }, "Geomorfologi": { "count": 1 }, "M\u00f8re og Romsdal": { "count": 3 }, "Fjord": { "count": 1 }, "Formering": { "count": 1 }, "Design": { "count": 4 }, "M\u00f8bler og interi\u00f8rtyper": { "count": 1 }, "Ordforklaringer": { "count": 10 }, "Uttrykk og ordtak": { "count": 3 }, "Petroleumsfelter": { "count": 2 }, "Brasils historie": { "count": 2 }, "Brasils samtidshistorie": { "count": 2 }, "Kildeskrifter": { "count": 3 }, "Norske slekter": { "count": 9 }, "Kamp- og kontaktsport": { "count": 2 }, "Asiatiske kampsporter": { "count": 1 }, "Stormfugler": { "count": 1 }, "Stormfuglfamilien": { "count": 1 }, "Thalassoica": { "count": 1 }, "Danmarks historie": { "count": 4 }, "Danmarks samtidshistorie": { "count": 1 }, "Personer innen astronomi": { "count": 3 }, "Romvirksomhet": { "count": 4 }, "Personer": { "count": 1 }, " bedrifter og organisasjoner innen romvirksomhet": { "count": 1 }, "Prefikser og suffikser": { "count": 1 }, "Kraftselskaper og kraftverk": { "count": 2 }, "Arkivfag": { "count": 2 }, "Vestfold og Telemark": { "count": 2 }, "Midt-Telemark": { "count": 1 }, "B\u00f8": { "count": 2 }, "Russlands geografi": { "count": 1 }, "Teknologi- og industrihistorie": { "count": 4 }, "Norsk teknologi- og industrihistorie": { "count": 4 }, "Bergverkshistorie": { "count": 1 }, "Statsvitere og institusjoner": { "count": 1 }, "Verdensmusikk": { "count": 2 }, "Country og bluegrass": { "count": 1 }, "Amerikanske country- og bluegrassartister": { "count": 1 }, "Barnehage": { "count": 2 }, "Internasjonale klassiske ensembler": { "count": 1 }, "Antikkens filosofi": { "count": 2 }, "Leppeblomstordenen": { "count": 3 }, "Kjempefamilien": { "count": 1 }, "Kjempeslekta": { "count": 1 }, "Industri": { "count": 4 }, "Metallarbeid": { "count": 2 }, "Geologer": { "count": 2 }, "Canadas historie": { "count": 1 }, "Canadas samtidshistorie": { "count": 1 }, "Sosiologisk teori": { "count": 4 }, "Palestinas historie": { "count": 2 }, "Palestinas samtidshistorie": { "count": 2 }, "Canadas franskspr\u00e5klige litteratur": { "count": 1 }, "Internasjonale tegnekunstnere": { "count": 2 }, "\u00d8sterrikes litteratur": { "count": 2 }, "\u00d8sterrikes litteratur f\u00f8r 1700-tallet": { "count": 1 }, "Str\u00e5lefinnefisker": { "count": 2 }, "Karpefisker": { "count": 1 }, "Karpefamilien": { "count": 1 }, "Rhodeus": { "count": 1 }, "Indonesias historie": { "count": 1 }, "Indonesias samtidshistorie": { "count": 1 }, "Samfunnssikkerhet og beredskap": { "count": 1 }, "Beredskap og kriseh\u00e5ndtering": { "count": 1 }, "Designteori og -historie": { "count": 1 }, "Grunnstoffer": { "count": 5 }, "Nyklassisisme og romantikk i bildende kunst": { "count": 1 }, "Rot hos planter": { "count": 1 }, "Kroatias litteratur": { "count": 1 }, "Flaggermus": { "count": 1 }, "Glattnesefamilien": { "count": 1 }, "Vespertilioninae": { "count": 1 }, "Plecotini": { "count": 1 }, "Barbastella": { "count": 1 }, "J\u00f8dedom": { "count": 2 }, "Tsjekkias geografi": { "count": 1 }, "Danmarks litteratur": { "count": 5 }, "Danmarks litteratur p\u00e5 1900-tallet": { "count": 4 }, "Fransk politikk": { "count": 1 }, "IT-historie": { "count": 1 }, "Personer i IT-historie": { "count": 1 }, "USAs litteratur 1900-1950": { "count": 1 }, "Internasjonal rett": { "count": 3 }, "Alminnelig folkerett": { "count": 3 }, "Lydteknologi": { "count": 1 }, "Flatormer": { "count": 1 }, "Bendelormer": { "count": 1 }, "Pseudophyllidea": { "count": 1 }, "Diphyllobothriidae": { "count": 1 }, "Asias litteratur": { "count": 3 }, "Irans litteratur": { "count": 1 }, "Realisme og impresjonisme": { "count": 5 }, "Kjernekjemi": { "count": 1 }, "Hellas\u2019 historie": { "count": 1 }, "Norske aviser": { "count": 2 }, "Ord og uttrykk p\u00e5 andre spr\u00e5k": { "count": 3 }, "Tyske ord og uttrykk": { "count": 2 }, "Storbritannia og Nord-Irlands litteratur p\u00e5 1600-tallet": { "count": 1 }, "Haier og skater": { "count": 1 }, "H\u00e5branner": { "count": 1 }, "Brugdefamilien": { "count": 1 }, "Cetorhinus": { "count": 1 }, "Rettskildel\u00e6re": { "count": 1 }, "Belgias historie": { "count": 1 }, "Usbekistans geografi": { "count": 1 }, "Elektronikk": { "count": 6 }, "Fjernsynsteknikk": { "count": 1 }, "Frankrikes litteratur f\u00f8r 1500-tallet": { "count": 1 }, "Begreper i botanikken": { "count": 2 }, "Costa Ricas litteratur": { "count": 1 }, "Macrocystidiaceae": { "count": 1 }, "Macrocystidia": { "count": 1 }, "Flagg og nasjonalsymboler": { "count": 2 }, "Flagg og v\u00e5pen": { "count": 2 }, "Milit\u00e6r teori": { "count": 1 }, "Arendal": { "count": 1 }, "Austrheim": { "count": 1 }, "Cubas historie": { "count": 1 }, "Cubas samtidshistorie": { "count": 1 }, "Motiver i bildende kunst": { "count": 1 }, "Strophariaceae": { "count": 1 }, "Skulptur og mosaikk i nyere tid": { "count": 3 }, "Europas \u00f8vrige historie": { "count": 3 }, "Europa p\u00e5 1900-tallet": { "count": 1 }, "Kjemiens historie": { "count": 1 }, "S\u00f8tvierordenen": { "count": 3 }, "S\u00f8tvierfamilien": { "count": 3 }, "S\u00f8tvierslekta": { "count": 2 }, "Andre verdenskrig": { "count": 2 }, "Tysklands litteratur p\u00e5 1800-tallet": { "count": 3 }, "Norske klassiske ensembler": { "count": 1 }, "Drammen": { "count": 1 }, "Perus geografi": { "count": 2 }, "Romobservatorier": { "count": 2 }, "Fagbegreper i antropologi": { "count": 3 }, "Botswanas historie": { "count": 1 }, "Botswanas samtidshistorie": { "count": 1 }, "Vortemelkfamilien": { "count": 2 }, "Fly- og helikopterprodusenter": { "count": 2 }, "Heraldikk": { "count": 1 }, "Grafikk": { "count": 1 }, "Genetikk": { "count": 2 }, "Bemannet romfart": { "count": 1 }, "Tyrkias geografi": { "count": 2 }, "Den katolske kirke": { "count": 1 }, "Erkebiskoper": { "count": 1 }, "Biografier i norsk teknologi- og industrihistorie": { "count": 2 }, "Vepser": { "count": 3 }, "Arverett og skifterett": { "count": 1 }, "\u00d8rland": { "count": 1 }, "Engelsk fotball": { "count": 2 }, "Engelske fotballspillere": { "count": 1 }, "Bibliotek": { "count": 1 }, "S\u00f8r-Amerikas litteratur": { "count": 2 }, "Colombias litteratur": { "count": 1 }, "Protestantisme": { "count": 4 }, "Samferdsel": { "count": 2 }, "Broer": { "count": 1 }, "Broer i Norge": { "count": 1 }, "Stilkvepser": { "count": 1 }, "Broddvepser": { "count": 1 }, "Apoidea": { "count": 1 }, "Grafisk industri": { "count": 3 }, "Teknologi og materialer i grafisk industri": { "count": 2 }, "Norske skuespillere": { "count": 4 }, "Aviser i Vestland": { "count": 1 }, "Magnoliids": { "count": 1 }, "Magnoliaordenen": { "count": 1 }, "Annonaceae": { "count": 1 }, "Den franske revolusjon": { "count": 1 }, "Teater": { "count": 1 }, "Internasjonale teaterinstitusjoner": { "count": 1 }, "Arkeologi": { "count": 9 }, "Nordisk arkeologi": { "count": 2 }, "Hvaler": { "count": 1 }, "Bardehvaler": { "count": 1 }, "Finnhvalfamilien": { "count": 1 }, "Balaenoptera": { "count": 1 }, "Folketro": { "count": 2 }, "Russland og Sovjetunionens historie": { "count": 5 }, "Russlands eldre historie": { "count": 3 }, "Blad": { "count": 1 }, "Europeiske filmskuespillere": { "count": 4 }, "Internasjonale klassiske komponister og verker i barokken": { "count": 2 }, "Samfunns\u00f8konomi": { "count": 1 }, "\u00d8konomisk politikk": { "count": 1 }, "Motorsport": { "count": 1 }, "Bilsport": { "count": 1 }, "Perus historie": { "count": 1 }, "Skipstekniske begrep": { "count": 2 }, "Glass og keramikk": { "count": 1 }, "Glass og keramikk \u2013 ut\u00f8vere": { "count": 1 }, "Brunrotfamilien": { "count": 1 }, "Bokkunst": { "count": 1 }, "Internasjonale klassiske instrumentalister": { "count": 1 }, "Dagblomordenen": { "count": 1 }, "Dagblomfamilien": { "count": 1 }, "Roseordenen": { "count": 1 }, "Rosefamilien": { "count": 1 }, "Epleslekta": { "count": 1 }, "USAs litteratur 1950-2000": { "count": 3 }, "Plantevepser": { "count": 1 }, "Tenthredinoidea": { "count": 1 }, "Bladvepser": { "count": 1 }, "Blennocampinae": { "count": 1 }, "Tomostethus": { "count": 1 }, "Franske s\u00f8rterritorier": { "count": 1 }, "Musikkinstrumenter": { "count": 1 }, "Elektriske musikkinstrumenter": { "count": 1 }, "Arbeidsrett": { "count": 1 }, "Optikk": { "count": 3 }, "Animasjonsfilm": { "count": 1 }, "Snipefamilien": { "count": 1 }, "Rogaland": { "count": 3 }, "Eigersund": { "count": 2 }, "Albanias historie": { "count": 2 }, "Sirenia": { "count": 1 }, "Dugongidae": { "count": 1 }, "Dugong": { "count": 1 }, "Dans": { "count": 5 }, "Scenisk dans": { "count": 2 }, "Moderne- og samtidsdans": { "count": 1 }, "Moderne- og samtidsdans: norske kunstnere og kompanier": { "count": 1 }, "Raketter": { "count": 2 }, "Obligasjonsrett": { "count": 4 }, "Myanmars historie": { "count": 1 }, "Myanmars samtidshistorie": { "count": 1 }, "Biografier i Romerrikets historie": { "count": 3 }, "Kantarellordenen": { "count": 1 }, "Clavulinaceae": { "count": 1 }, "Ringerike": { "count": 1 }, "Litteraturtyper": { "count": 7 }, "Barne- og ungdomslitteratur": { "count": 3 }, "Internasjonal barne- og ungdomslitteratur": { "count": 2 }, "Russland og Sovjetunionens litteratur": { "count": 1 }, "Russiske litteraturforskere og kritikere": { "count": 1 }, "Filippinenes historie": { "count": 1 }, "Filippinenes samtidshistorie": { "count": 1 }, "Norske jazzut\u00f8vere og -ensembler": { "count": 2 }, "Bedrifts\u00f8konomi": { "count": 5 }, "Norske tegnekunstnere": { "count": 2 }, "Argentinas litteratur": { "count": 1 }, "Islands geografi": { "count": 1 }, "Gnagere": { "count": 2 }, "Sciuromorpha": { "count": 1 }, "Ekornfamilien": { "count": 1 }, "Myosciurus": { "count": 1 }, "Paleontologi": { "count": 5 }, "Tokke": { "count": 1 }, "Soul og R&B": { "count": 1 }, "Internasjonal soul og R&B": { "count": 1 }, "Utenlandske spr\u00e5kforskere": { "count": 1 }, "Forglemmegeislekta": { "count": 2 }, "Slimriket": { "count": 1 }, "Strafferett": { "count": 1 }, "Mineraler": { "count": 4 }, "Silikatmineraler": { "count": 3 }, "Norges forsvar": { "count": 2 }, "Norske festninger og milit\u00e6ranlegg": { "count": 1 }, "Katolske ritualer og symboler": { "count": 2 }, "Irlands geografi": { "count": 1 }, "Jurister": { "count": 2 }, "Ulike lands musikk og musikktradisjoner": { "count": 1 }, "Albanias samtidshistorie": { "count": 1 }, "Varehandel": { "count": 1 }, "Psykologiens historie": { "count": 1 }, "Utenlandske aviser": { "count": 2 }, "Verdenshavene": { "count": 3 }, "Dyphavsgroper": { "count": 1 }, "Ulike lands arkitekturhistorie": { "count": 1 }, "Islands litteratur": { "count": 4 }, "Ulike lands kunst og kunsttradisjoner": { "count": 1 }, "Konstruksjonsteknikk": { "count": 1 }, "Canadas geografi": { "count": 1 }, "Bakterier": { "count": 1 }, "H\u00e5ndverk": { "count": 1 }, "Redskaper og festemidler": { "count": 1 }, "Utforsking av solsystemet": { "count": 1 }, "Vin i Europa": { "count": 1 }, "Vin i Frankrike": { "count": 1 }, "Myndigheter i Norge": { "count": 2 }, "Embets- og tjenestepersoner": { "count": 1 }, "Det 19. \u00e5rhundres filosofi": { "count": 1 }, "Nederlands historie": { "count": 1 }, "Norges historie fram til 1050": { "count": 1 }, "Barnevern": { "count": 1 }, "Rovpattedyr": { "count": 2 }, "Caniformia": { "count": 2 }, "Bj\u00f8rnefamilien": { "count": 1 }, "Tremarctos": { "count": 1 }, "Kirgisistans historie": { "count": 1 }, "Kirgisistans samtidshistorie": { "count": 1 }, "Krypdyr": { "count": 1 }, "Dinosaurer": { "count": 1 }, "\u00d8vrig europeisk malerkunst 1400-1750": { "count": 2 }, "Mesopotamia": { "count": 2 }, "Storg\u00e5rder og herreg\u00e5rder": { "count": 2 }, "Norske storg\u00e5rder": { "count": 2 }, "Internasjonale arkitekter og arkitektkontorer fra 1900 til i dag": { "count": 4 }, "Skriftspr\u00e5k": { "count": 1 }, "Alfabeter og skriftsystemer": { "count": 1 }, "Skrifttegn": { "count": 1 }, "Latinske bokstaver": { "count": 1 }, "Diakritiske tegn": { "count": 1 }, "Det 17. og 18. \u00e5rhundres filosofi": { "count": 2 }, "Norske arkitekter og arkitektkontorer fra 1900 til i dag": { "count": 3 }, "Asias kj\u00f8kken": { "count": 1 }, "Avisjournalister": { "count": 1 }, "V\u00e5pen": { "count": 2 }, "Artilleri": { "count": 1 }, "TV og radio": { "count": 1 }, "TV- og radiopersoner": { "count": 1 }, "Uorganisk kjemi": { "count": 3 }, "Myomorpha": { "count": 1 }, "Muroidea": { "count": 1 }, "Hamsterfamilien": { "count": 1 }, "Arvicolinae": { "count": 1 }, "Lemmini": { "count": 1 }, "Lemmus": { "count": 1 }, "Bilens drivlinje": { "count": 1 }, "Britisk Indiahav": { "count": 1 }, "Nyrealisme": { "count": 1 }, " nysaklighet og tendenskunst": { "count": 1 }, "Cellebiologi": { "count": 1 }, "Cellestrukturer": { "count": 1 }, "Tysklands geografi": { "count": 3 }, "Armenias geografi": { "count": 1 }, "Elektronisk navigasjon": { "count": 1 }, "Kinematografi": { "count": 1 }, "Spr\u00e5kfamilier": { "count": 3 }, "Indoeuropeiske spr\u00e5k": { "count": 3 }, "Romansk": { "count": 2 }, "Latin": { "count": 2 }, "Latinske verk": { "count": 2 }, "Folkegrupper i Asia": { "count": 1 }, "Folkegrupper i Sentral-Asia": { "count": 1 }, "Bilmerker": { "count": 2 }, "Eritreas geografi": { "count": 1 }, "Norr\u00f8n litteratur": { "count": 2 }, "Algebra": { "count": 1 }, "Kommutative algebraer og ringer": { "count": 1 }, "Israels geografi": { "count": 1 }, "Nellikordenen": { "count": 1 }, "Slireknefamilien": { "count": 1 }, "Syreslekta": { "count": 1 }, "And\u00f8y": { "count": 1 }, "Gulen": { "count": 1 }, "Rettshistorie": { "count": 2 }, "Kvinnherad": { "count": 1 }, "Bilhistoriske biografier": { "count": 1 }, "Jordans historie": { "count": 1 }, "Friidrett": { "count": 1 }, "L\u00f8p": { "count": 1 }, "Europeiske filmskapere": { "count": 1 }, "Oseania generelt": { "count": 1 }, "Industridesign": { "count": 1 }, "Fast eiendom": { "count": 1 }, "Milit\u00e6rvesen": { "count": 2 }, "Bank og finans": { "count": 2 }, "B\u00f8rs og finans": { "count": 2 }, "Internasjonale klassiske sangere": { "count": 2 }, "Nattravn- og seilerfugler": { "count": 1 }, "Seilerfamilien": { "count": 1 }, "Tachymarptis": { "count": 1 }, "Zoologi": { "count": 1 }, "Pedagogisk teori": { "count": 1 }, "Midt\u00f8sten": { "count": 4 }, "Midt\u00f8stens gamle kulturer": { "count": 4 }, "Oppdagelsesreiser": { "count": 3 }, "Urstilksporesopper": { "count": 1 }, "Ekte rustsopper": { "count": 1 }, "Rustsoppordenen": { "count": 1 }, "Pucciniaceae": { "count": 1 }, "Slektskap": { "count": 1 }, " familie og ekteskap": { "count": 1 }, "Akershus": { "count": 1 }, "Sk\u00f8ytesport": { "count": 1 }, "Eldre mynter og pengeenheter": { "count": 2 }, "Elektronisk musikk": { "count": 1 }, "Kunstinstitusjoner": { "count": 1 }, "Internasjonale kunstinstitusjoner": { "count": 1 }, "Norges historie fra 1884 til 1940": { "count": 5 }, "Plantefysiologi": { "count": 1 }, "Serbias historie": { "count": 1 }, "Ulike lands dansehistorie": { "count": 1 }, "Spanias litteratur": { "count": 1 }, "Spanias litteratur p\u00e5 1900-tallet": { "count": 1 }, "Israels litteratur": { "count": 1 }, "Skytesport": { "count": 1 }, "Viltm\u00e5l": { "count": 1 }, "H\u00e6r og landforsvar": { "count": 1 }, "Norsk og samisk litteratur": { "count": 11 }, "Nyere norsk litteratur": { "count": 5 }, "Italienske ord og uttrykk": { "count": 1 }, "USAs nyere litteratur": { "count": 2 }, "Nyklassisisme og historisme i arkitekturhistorien": { "count": 2 }, "Hygrophoraceae": { "count": 1 }, "Cuphophyllus": { "count": 1 }, "Ustabile grunnstoffer": { "count": 3 }, "Kubisme og futurisme": { "count": 1 }, "Krim": { "count": 1 }, "Krim i Norge": { "count": 1 }, "Namibias historie": { "count": 1 }, "Skifer": { "count": 1 }, "Rytme og tempo": { "count": 1 }, "Bl\u00f8tdyr": { "count": 2 }, "Snegler": { "count": 1 }, "Albuesnegler": { "count": 1 }, "Patelloidea": { "count": 1 }, "Patellidae": { "count": 1 }, "Patella": { "count": 1 }, "Angolas historie": { "count": 1 }, "Angolas samtidshistorie": { "count": 1 }, "Grunnoppl\u00e6ring": { "count": 2 }, "Yrkesfaglig utdanning": { "count": 2 }, "Bygg- og anleggsteknikk": { "count": 1 }, "Sveriges geografi": { "count": 3 }, "Andefugler": { "count": 1 }, "Andefamilien": { "count": 1 }, "Somateria": { "count": 1 }, "Rugby og amerikansk fotball": { "count": 1 }, "Broddsoppordenen": { "count": 1 }, "Hymenochaetaceae": { "count": 1 }, "Jordbruk": { "count": 1 }, "Trelast og treforedling": { "count": 2 }, "Papirindustri": { "count": 1 }, "Venezuelas geografi": { "count": 1 }, "Mystikere": { "count": 1 }, "Prosess": { "count": 1 }, "Straffeprosess": { "count": 1 }, "Institusjoner i klassisk musikk": { "count": 1 }, "Aviseiere og direkt\u00f8rer": { "count": 2 }, "Nord-amerikanske filmskapere": { "count": 2 }, "Norske kirkebygg": { "count": 2 }, "Utdanning i verden": { "count": 2 }, "Utdanning i Europa": { "count": 1 }, "Marokkos geografi": { "count": 1 }, "Trolldomsprosesser": { "count": 1 }, "Etiopias geografi": { "count": 1 }, "Petroleumshistorie": { "count": 1 }, "Ulykker i petroleumsbransjen": { "count": 1 }, "Anvendt elektromagnetisme": { "count": 1 }, "Tyrkiskspr\u00e5klig litteratur": { "count": 1 }, "Tyrkias litteratur": { "count": 1 }, "Indre \u00d8stfold": { "count": 1 }, "Eidsberg": { "count": 1 }, "Grafisk industrihistorie": { "count": 1 }, "Tingvoll": { "count": 1 }, "\u00d8kologi": { "count": 1 }, "Utviklingsbiologi": { "count": 1 }, "Fiskeri og havbruk": { "count": 1 }, "Norske fiskerier": { "count": 1 }, "Fiskeredskaper og fart\u00f8y": { "count": 1 }, "Bulgarias geografi": { "count": 2 }, "Nyere norsk sakprosa": { "count": 1 }, "Tremellomycetes": { "count": 1 }, "Tremellales": { "count": 1 }, "Tremellaceae": { "count": 1 }, "Cryptococcus": { "count": 1 }, "Norges litteratur 1800-tallet": { "count": 1 }, "Forskning og h\u00f8yere utdanning": { "count": 2 }, "Forskningsinstitutter": { "count": 1 }, "Transportrett": { "count": 2 }, "Sj\u00f8rett": { "count": 2 }, "Italias historie": { "count": 2 }, "Italias samtidshistorie": { "count": 1 }, "Internasjonale milit\u00e6re biografier": { "count": 2 }, "Portugisisk fotball": { "count": 1 }, "Medisin": { "count": 3 }, "Helse og samfunn": { "count": 2 }, "Medisinsk historie": { "count": 2 }, "Algeries geografi": { "count": 1 }, "Sveits\u2019 geografi": { "count": 2 }, "Klovdyr": { "count": 1 }, "Kvegfamilien": { "count": 1 }, "Bos": { "count": 1 }, "Norges litteratur 1900-1960": { "count": 1 }, "Mel\u00f8y": { "count": 1 }, "Religionsfilosofi": { "count": 1 }, "Sveits\u2019 litteratur": { "count": 2 }, "Sveits\u2019 franskspr\u00e5klige litteratur": { "count": 1 }, "Materialfysikk": { "count": 1 }, "Systematikk i biologien": { "count": 1 }, "Terrorisme": { "count": 1 }, "Norsk barne- og ungdomslitteratur f\u00f8r 2000": { "count": 1 }, "Krystallografi": { "count": 1 }, "Litter\u00e6re perioder og stiler": { "count": 1 }, "Ungarns litteratur": { "count": 1 }, "Semantikk": { "count": 1 }, "Norsk samtidskunst": { "count": 2 }, "Enebakk": { "count": 1 }, "Europeisk arkeologi": { "count": 1 }, "Tidlig abstrakt billedkunst": { "count": 1 }, "Cortinariaceae": { "count": 1 }, "Sl\u00f8rsopper": { "count": 1 }, "Sentralafrikanske republikks historie": { "count": 1 }, "Nord-Makedonias historie": { "count": 1 }, "Nord-Makedonias samtidshistorie": { "count": 1 }, "Ford\u00f8yelsessystemet": { "count": 1 }, "Ern\u00e6ring": { "count": 1 }, "Sveits\u2019 historie": { "count": 1 }, "Sveits\u2019 samtidshistorie": { "count": 1 }, "Grader og titler": { "count": 1 }, "Akademiske titler": { "count": 1 }, "New Zealands geografi": { "count": 1 }, "Sveriges historie": { "count": 1 }, "Sveriges kongehus": { "count": 1 }, "Norges historie fra 1940 til 1945": { "count": 2 }, "Klassisk religion": { "count": 1 }, "Astronomisk teknologi": { "count": 1 }, "Spanias historie": { "count": 1 }, "Spanias samtidshistorie": { "count": 1 }, "Sjangerl\u00e6re": { "count": 2 }, "epikk": { "count": 1 }, "Eidfjord": { "count": 1 }, "Orientering": { "count": 1 }, "Skotsk fotball": { "count": 1 }, "Leppeblomstfamilien": { "count": 1 }, "D\u00e5slekta": { "count": 1 }, "Estetikk": { "count": 2 }, "Nigerias historie": { "count": 1 }, "Nigerias samtidshistorie": { "count": 1 }, "Musikaler": { "count": 2 }, "Angolas geografi": { "count": 1 }, "Kristne ritualer og symboler": { "count": 2 }, "Radioteknikk": { "count": 1 }, "Internasjonale fotografer og fotokunstnere": { "count": 1 }, "Internasjonale klassiske komponister og verker 1900\u20131950": { "count": 2 }, "Norsk bildende kunst fra 1945 til 1990": { "count": 2 }, "Serbia og det gamle Jugoslavias litteratur": { "count": 1 }, "Polare ekspedisjoner og oppdagere": { "count": 1 }, "Italiensk fotball": { "count": 1 }, "Petroleumsselskaper": { "count": 1 }, "Datoartikler": { "count": 3 }, "Tysklands litteratur 1950-2000": { "count": 1 }, "M\u00e5ltider": { "count": 1 }, "Iraks historie": { "count": 1 }, "Iraks samtidshistorie": { "count": 1 }, "Irans historie": { "count": 1 }, "Irans samtidshistorie": { "count": 1 }, "Bod\u00f8": { "count": 1 }, "Nordiske jazzut\u00f8vere og -ensembler": { "count": 2 }, " 1980 til idag": { "count": 2 }, "Trelast- og treforedlingsindustri \u2013 historie": { "count": 1 }, "Det gamle Egypt": { "count": 1 }, "Norske ord og uttrykk": { "count": 1 }, "Papua Ny-Guineas geografi": { "count": 1 }, "Asker": { "count": 1 }, "Amfibier": { "count": 2 }, "Springpadder": { "count": 1 }, "Eleutherodactylidae": { "count": 1 }, "Eleutherodactylus": { "count": 1 }, "Tunneler": { "count": 1 }, "Tunneler i Norge": { "count": 1 }, "Salamandere": { "count": 1 }, "Plethodontidae": { "count": 1 }, "Aneides": { "count": 1 }, "H\u00e6ren": { "count": 1 }, "Kardeborreordenen": { "count": 1 }, "Kaprifolfamilien": { "count": 1 }, "Bl\u00e5knappslekta": { "count": 1 }, "Italias litteratur p\u00e5 1700-tallet": { "count": 1 }, "Skipsbygging": { "count": 1 }, "Skipskonstrukt\u00f8rer": { "count": 1 }, "Piggepleslekta": { "count": 1 }, "Sediment\u00e6re bergarter": { "count": 1 }, "Samfunnstyper": { "count": 1 }, "Boksing": { "count": 1 }, "Designinstitusjoner": { "count": 1 }, "De forente arabiske emiraters historie": { "count": 1 }, "De forente arabiske emiraters samtidshistorie": { "count": 1 }, "Folketrygd og pensjon": { "count": 1 }, "Forbrukerelektronikk": { "count": 1 }, "Utdanning i S\u00f8r-Amerika": { "count": 1 }, "Asias geografi generelt": { "count": 1 }, "Urverk og klokker": { "count": 1 }, "Standardisering": { "count": 1 }, "Oppdal": { "count": 1 }, "Norske arkitekturinstitusjoner": { "count": 1 }, "Sparta": { "count": 1 }, "Kunsth\u00e5ndverk": { "count": 2 }, "Treskurd": { "count": 1 }, "Treskj\u00e6rere": { "count": 1 }, "Tysklands historie fra 1806 til 1918": { "count": 1 }, "Mexicos geografi": { "count": 1 }, "Selfamilien": { "count": 1 }, "Cystophora": { "count": 1 }, "Burundis geografi": { "count": 1 }, "Islands historie": { "count": 1 }, "Tegneserier": { "count": 1 }, "Birkenes": { "count": 1 }, "Humanetikk": { "count": 1 }, "Matretter": { "count": 2 }, "Supper": { "count": 2 }, " sauser og kraft": { "count": 2 }, "Ugandas historie": { "count": 1 }, "Erkjennelsesteori": { "count": 1 }, "Sveits\u2019 tyskspr\u00e5klig litteratur": { "count": 1 }, "Sveits\u2019 tyskspr\u00e5klig litteratur p\u00e5 1900-tallet": { "count": 1 }, "Popkunst og minimalisme": { "count": 1 }, "Klassisk ballett": { "count": 1 }, "Klassisk ballett: internasjonale kunstnere og kompanier": { "count": 1 }, "Inkludering og rettigheter": { "count": 1 }, "Likestilling og diskriminering": { "count": 1 }, "Kvinnebevegelse": { "count": 1 }, "Kvinnebevegelsen i Norge": { "count": 1 }, "Arkeologi i Asia": { "count": 1 }, "Cubas litteratur": { "count": 1 }, "Elektrokjemi": { "count": 1 }, "Norges litteratur 1960-2000": { "count": 3 }, "Nederlands litteratur": { "count": 1 }, "Forfattere i romerrikets litteratur": { "count": 1 }, "Forbrenningsmotorer": { "count": 2 }, "Vitenskapsteori": { "count": 1 }, "Vitenskapsteoretikere": { "count": 1 }, "Norsk lyrikk 1960-2000": { "count": 1 }, "Helserett": { "count": 1 }, "Klesplagg": { "count": 1 }, "Belgias geografi": { "count": 1 }, "Antarktis": { "count": 1 }, "Danseinstitusjoner": { "count": 1 }, "Irans geografi": { "count": 1 }, "V\u00e5rskrinneblomslekta": { "count": 1 }, "Motstandskampen i Norge": { "count": 1 }, "Skjell": { "count": 1 }, "Unionoida": { "count": 1 }, "Unionoidea": { "count": 1 }, "Elvemuslinger": { "count": 1 }, "Margaritifera": { "count": 2 }, "Klassisk arkeologi": { "count": 1 }, "Gresk arkeologi": { "count": 1 }, "Teknologi- og industrifag": { "count": 1 }, "Afrosoricida": { "count": 1 }, "Tenrecidae": { "count": 1 }, "Tysklands historie fra 1918 til 1933": { "count": 1 }, "Erstatningsrett": { "count": 1 }, "Trevirke": { "count": 1 }, "Sovjetunionens historie": { "count": 2 }, "Gjenstanders kulturhistorie": { "count": 2 }, "Dominicas geografi": { "count": 2 }, "B\u00f8keordenen": { "count": 1 }, "Bj\u00f8rkefamilien": { "count": 1 }, "Bj\u00f8rkeslekta": { "count": 1 }, "Metrikk": { "count": 1 }, "USAs historie 1920\u20131960": { "count": 2 }, "Energi og ressurs": { "count": 1 }, "Tysklands nyere litteratur": { "count": 1 }, "Libanons historie": { "count": 1 }, "B\u00e6rum": { "count": 1 }, "Brasils geografi": { "count": 1 }, "Norges historie fra 1300 til 1660": { "count": 1 }, "Natur og landemerker i USA": { "count": 2 }, "Kv\u00e6fjord": { "count": 1 }, "Fremmedord og l\u00e5nord": { "count": 2 }, "Lokalforvaltning": { "count": 1 }, "Brennevin": { "count": 1 }, "Drinker": { "count": 1 }, "Hest": { "count": 1 }, "Erteblomstordenen": { "count": 1 }, "Erteblomstfamilien": { "count": 1 }, "Acacia": { "count": 1 }, "Historiske biografier i norsk politikk": { "count": 1 }, "Fremmedord med latinsk og gresk opphav": { "count": 1 }, "B\u00e5tsfjord": { "count": 1 }, "Tidsskrifter": { "count": 1 }, "Romanias samtidshistorie": { "count": 1 }, "Fagretninger i sosiologi": { "count": 1 }, "Folkegrupper i S\u00f8r-Amerika": { "count": 1 }, "Norges historie generelt": { "count": 1 }, "Norsk polarhistorie": { "count": 1 }, "Tekstilkunst": { "count": 1 }, "Tekstilkunstnere": { "count": 1 }, "Arkeologer": { "count": 2 }, "Stabile grunnstoffer": { "count": 1 }, "Fiskenes anatomi og fysiologi": { "count": 1 }, "Vang": { "count": 1 }, "Sunnfjord": { "count": 1 }, "Samv\u00e6rsdans": { "count": 1 }, "Nicaraguas litteratur": { "count": 1 }, "Sulfid- og sulfatmineraler": { "count": 1 }, "Hardrock og heavy metal": { "count": 1 }, "Norsk hardrock og heavy metal": { "count": 1 }, "Aver\u00f8y": { "count": 1 }, "Sol og stjerner": { "count": 1 }, "Gloppen": { "count": 1 }, "Italiensk manierisme": { "count": 1 }, " barokk- og renessansekunst": { "count": 1 }, "Sakprosa": { "count": 1 }, "Sekksporesopper": { "count": 1 }, "Ursekksporesopper": { "count": 1 }, "Heksekostsopper": { "count": 1 }, "Religion i ulike land": { "count": 1 }, "Religion i Latin-Amerika": { "count": 1 }, "Italias nyere litteratur": { "count": 1 }, "Arkitekturteori og -metode": { "count": 1 }, "Bahrains geografi": { "count": 1 }, "Biografier i nyere norsk historie": { "count": 1 }, "Askvoll": { "count": 1 }, "\u00d8sterrikes litteratur p\u00e5 1900-tallet": { "count": 1 }, "Katt": { "count": 1 }, "Piggfinnefisker": { "count": 1 }, "Leppefiskfamilien": { "count": 1 }, "Ctenolabrus": { "count": 1 }, "Mykologi": { "count": 1 }, "Innholdsstoffer hos sopp": { "count": 1 }, "Fluesnapperfamilien": { "count": 1 }, "Luscinia": { "count": 1 }, "Colombias historie": { "count": 1 }, "\u00d8vrige indo-europeiske spr\u00e5k": { "count": 1 }, "Dannmarks historie 1814-1945": { "count": 1 }, "Arbeiderbevegelsens historie": { "count": 1 }, "Kameruns litteratur": { "count": 1 }, "Vannsport": { "count": 1 }, "Sv\u00f8mmesport": { "count": 1 }, "Abstrakt ekspresjonisme": { "count": 1 }, "Bulgarias historie": { "count": 1 }, "Storbritannia og Nord-Irlands litteratur p\u00e5 1800-tallet": { "count": 1 }, "Norske klassiske komponister og verker f\u00f8r 1900": { "count": 1 }, "Kirgisistans geografi": { "count": 1 }, "Panamas historie": { "count": 1 }, "Finlands geografi": { "count": 1 }, "Petroleumsprodukter": { "count": 1 }, "Teknisk kybernetikk": { "count": 1 }, "Dyregeografi": { "count": 1 }, "Verdens dyreliv": { "count": 1 }, "Minev\u00e5pen": { "count": 1 }, "Det bysantinske rike": { "count": 1 }, "Element\u00e6rpartikkelfysikk": { "count": 1 } } } } ``` </details> --- *This dataset card was automatically generated using [MTEB](https://github.com/embeddings-benchmark/mteb)*

Fhrozen/FSD50k

Fhrozen

2025-05-17T02:38:53Z

281

6

[ "task_categories:audio-classification", "annotations_creators:unknown", "language_creators:unknown", "source_datasets:unknown", "license:cc-by-4.0", "size_categories:10K<n<100K", "modality:audio", "arxiv:2010.00475", "region:us", "audio-slot-filling" ]

[ "audio-classification" ]

2022-05-06T08:51:56Z

0

--- annotations_creators: - unknown language_creators: - unknown license: cc-by-4.0 size_categories: - 10K<n<100K source_datasets: - unknown task_categories: - audio-classification task_ids: [] tags: - audio-slot-filling --- # Freesound Dataset 50k (FSD50K) ## Important **This data set is a copy from the original one located at Zenodo.** ## Dataset Description - **Homepage:** [FSD50K](https://zenodo.org/record/4060432) - **Repository:** [GitHub](https://github.com/edufonseca/FSD50K_baseline) - **Paper:** [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://arxiv.org/abs/2010.00475) - **Leaderboard:** [Paperswithcode Leaderboard](https://paperswithcode.com/dataset/fsd50k) ## Citation If you use the FSD50K dataset, or part of it, please cite our paper: >Eduardo Fonseca, Xavier Favory, Jordi Pons, Frederic Font, Xavier Serra. "FSD50K: an Open Dataset of Human-Labeled Sound Events", arXiv 2020. ### Data curators Eduardo Fonseca, Xavier Favory, Jordi Pons, Mercedes Collado, Ceren Can, Rachit Gupta, Javier Arredondo, Gary Avendano and Sara Fernandez ### Contact You are welcome to contact Eduardo Fonseca should you have any questions at [email protected]. ## About FSD50K Freesound Dataset 50k (or **FSD50K** for short) is an open dataset of human-labeled sound events containing 51,197 <a href="https://freesound.org/">Freesound</a> clips unequally distributed in 200 classes drawn from the <a href="https://research.google.com/audioset/ontology/index.html">AudioSet Ontology</a> [1]. FSD50K has been created at the <a href="https://www.upf.edu/web/mtg">Music Technology Group of Universitat Pompeu Fabra</a>. What follows is a brief summary of FSD50K's most important characteristics. Please have a look at our paper (especially Section 4) to extend the basic information provided here with relevant details for its usage, as well as discussion, limitations, applications and more. **Basic characteristics:** - FSD50K is composed mainly of sound events produced by physical sound sources and production mechanisms. - Following AudioSet Ontology’s main families, the FSD50K vocabulary encompasses mainly *Human sounds*, *Sounds of things*, *Animal*, *Natural sounds* and *Music*. - The dataset has 200 sound classes (144 leaf nodes and 56 intermediate nodes) hierarchically organized with a subset of the AudioSet Ontology. The vocabulary can be inspected in `vocabulary.csv` (see Files section below). - FSD50K contains 51,197 audio clips totalling 108.3 hours of audio. - The audio content has been manually labeled by humans following a data labeling process using the <a href="https://annotator.freesound.org/">Freesound Annotator</a> platform [2]. - Clips are of variable length from 0.3 to 30s, due to the diversity of the sound classes and the preferences of Freesound users when recording sounds. - Ground truth labels are provided at the clip-level (i.e., weak labels). - The dataset poses mainly a multi-label sound event classification problem (but also allows a variety of sound event research tasks, see Sec. 4D). - All clips are provided as uncompressed PCM 16 bit 44.1 kHz mono audio files. - The audio clips are grouped into a development (*dev*) set and an evaluation (*eval*) set such that they do not have clips from the same Freesound uploader. **Dev set:** - 40,966 audio clips totalling 80.4 hours of audio - Avg duration/clip: 7.1s - 114,271 smeared labels (i.e., labels propagated in the upwards direction to the root of the ontology) - Labels are correct but could be occasionally incomplete - A train/validation split is provided (Sec. 3H). If a different split is used, it should be specified for reproducibility and fair comparability of results (see Sec. 5C of our paper) **Eval set:** - 10,231 audio clips totalling 27.9 hours of audio - Avg duration/clip: 9.8s - 38,596 smeared labels - Eval set is labeled exhaustively (labels are correct and complete for the considered vocabulary) **NOTE:** All classes in FSD50K are represented in AudioSet, except `Crash cymbal`, `Human group actions`, `Human voice`, `Respiratory sounds`, and `Domestic sounds, home sounds`. ## License All audio clips in FSD50K are released under Creative Commons (CC) licenses. Each clip has its own license as defined by the clip uploader in Freesound, some of them requiring attribution to their original authors and some forbidding further commercial reuse. For attribution purposes and to facilitate attribution of these files to third parties, we include a mapping from the audio clips to their corresponding licenses. The licenses are specified in the files `dev_clips_info_FSD50K.json` and `eval_clips_info_FSD50K.json`. These licenses are CC0, CC-BY, CC-BY-NC and CC Sampling+. In addition, FSD50K as a whole is the result of a curation process and it has an additional license: FSD50K is released under <a href="https://creativecommons.org/licenses/by/4.0/">CC-BY</a>. This license is specified in the `LICENSE-DATASET` file downloaded with the `FSD50K.doc` zip file. ## Files FSD50K can be downloaded as a series of zip files with the following directory structure: <div class="highlight"><pre><span></span>root │ └───clips/ Audio clips │ │ │ └─── dev/ Audio clips in the dev set │ │ │ └─── eval/ Audio clips in the eval set │ └───labels/ Files for FSD50K's ground truth │ │ │ └─── dev.csv Ground truth for the dev set │ │ │ └─── eval.csv Ground truth for the eval set │ │ │ └─── vocabulary.csv List of 200 sound classes in FSD50K │ └───metadata/ Files for additional metadata │ │ │ └─── class_info_FSD50K.json Metadata about the sound classes │ │ │ └─── dev_clips_info_FSD50K.json Metadata about the dev clips │ │ │ └─── eval_clips_info_FSD50K.json Metadata about the eval clips │ │ │ └─── pp_pnp_ratings_FSD50K.json PP/PNP ratings │ │ │ └─── collection/ Files for the *sound collection* format │ │ └───README.md The dataset description file that you are reading │ └───LICENSE-DATASET License of the FSD50K dataset as an entity </pre></div> Each row (i.e. audio clip) of `dev.csv` contains the following information: - `fname`: the file name without the `.wav` extension, e.g., the fname `64760` corresponds to the file `64760.wav` in disk. This number is the Freesound id. We always use Freesound ids as filenames. - `labels`: the class labels (i.e., the ground truth). Note these class labels are *smeared*, i.e., the labels have been propagated in the upwards direction to the root of the ontology. More details about the label smearing process can be found in Appendix D of our paper. - `mids`: the Freebase identifiers corresponding to the class labels, as defined in the <a href="https://github.com/audioset/ontology/blob/master/ontology.json">AudioSet Ontology specification</a> - `split`: whether the clip belongs to *train* or *val* (see paper for details on the proposed split) Rows in `eval.csv` follow the same format, except that there is no `split` column. **NOTE:** We use a slightly different format than AudioSet for the naming of class labels in order to avoid potential problems with spaces, commas, etc. Example: we use `Accelerating_and_revving_and_vroom` instead of the original `Accelerating, revving, vroom`. You can go back to the original AudioSet naming using the information provided in `vocabulary.csv` (class label and mid for the 200 classes of FSD50K) and the <a href="https://github.com/audioset/ontology/blob/master/ontology.json">AudioSet Ontology specification</a>. ### Files with additional metadata (metadata/) To allow a variety of analysis and approaches with FSD50K, we provide the following metadata: 1. `class_info_FSD50K.json`: python dictionary where each entry corresponds to one sound class and contains: `FAQs` utilized during the annotation of the class, `examples` (representative audio clips), and `verification_examples` (audio clips presented to raters during annotation as a quality control mechanism). Audio clips are described by the Freesound id. **NOTE:** It may be that some of these examples are not included in the FSD50K release. 2. `dev_clips_info_FSD50K.json`: python dictionary where each entry corresponds to one dev clip and contains: title, description, tags, clip license, and the uploader name. All these metadata are provided by the uploader. 3. `eval_clips_info_FSD50K.json`: same as before, but with eval clips. 4. `pp_pnp_ratings.json`: python dictionary where each entry corresponds to one clip in the dataset and contains the PP/PNP ratings for the labels associated with the clip. More specifically, these ratings are gathered for the labels validated in **the validation task** (Sec. 3 of paper). This file includes 59,485 labels for the 51,197 clips in FSD50K. Out of these labels: - 56,095 labels have inter-annotator agreement (PP twice, or PNP twice). Each of these combinations can be occasionally accompanied by other (non-positive) ratings. - 3390 labels feature other rating configurations such as *i)* only one PP rating and one PNP rating (and nothing else). This can be considered inter-annotator agreement at the ``Present” level; *ii)* only one PP rating (and nothing else); *iii)* only one PNP rating (and nothing else). Ratings' legend: PP=1; PNP=0.5; U=0; NP=-1. **NOTE:** The PP/PNP ratings have been provided in the *validation* task. Subsequently, a subset of these clips corresponding to the eval set was exhaustively labeled in the *refinement* task, hence receiving additional labels in many cases. For these eval clips, you might want to check their labels in `eval.csv` in order to have more info about their audio content (see Sec. 3 for details). 5. `collection/`: This folder contains metadata for what we call the ***sound collection format***. This format consists of the raw annotations gathered, featuring all generated class labels without any restriction. We provide the *collection* format to make available some annotations that do not appear in the FSD50K *ground truth* release. This typically happens in the case of classes for which we gathered human-provided annotations, but that were discarded in the FSD50K release due to data scarcity (more specifically, they were merged with their parents). In other words, the main purpose of the `collection` format is to make available annotations for tiny classes. The format of these files in analogous to that of the files in `FSD50K.ground_truth/`. A couple of examples show the differences between **collection** and **ground truth** formats: `clip`: `labels_in_collection` -- `labels_in_ground_truth` `51690`: `Owl` -- `Bird,Wild_Animal,Animal` `190579`: `Toothbrush,Electric_toothbrush` -- `Domestic_sounds_and_home_sounds` In the first example, raters provided the label `Owl`. However, due to data scarcity, `Owl` labels were merged into their parent `Bird`. Then, labels `Wild_Animal,Animal` were added via label propagation (smearing). The second example shows one of the most extreme cases, where raters provided the labels `Electric_toothbrush,Toothbrush`, which both had few data. Hence, they were merged into Toothbrush's parent, which unfortunately is `Domestic_sounds_and_home_sounds` (a rather vague class containing a variety of children sound classes). **NOTE:** Labels in the collection format are not smeared. **NOTE:** While in FSD50K's ground truth the vocabulary encompasses 200 classes (common for dev and eval), since the *collection* format is composed of raw annotations, the vocabulary here is much larger (over 350 classes), and it is slightly different in dev and eval. For further questions, please contact [email protected], or join the <a href="https://groups.google.com/g/freesound-annotator">freesound-annotator Google Group</a>. ## Download Clone this repository: ``` git clone https://huggingface.co/Fhrozen/FSD50k ``` ## Baseline System Several baseline systems for FSD50K are available at <a href="https://github.com/edufonseca/FSD50K_baseline">https://github.com/edufonseca/FSD50K_baseline</a>. The experiments are described in Sec 5 of our paper. ## References and links [1] Jort F Gemmeke, Daniel PW Ellis, Dylan Freedman, Aren Jansen, Wade Lawrence, R Channing Moore, Manoj Plakal, and Marvin Ritter. "Audio set: An ontology and human-labeled dataset for audio events." In Proceedings of the International Conference on Acoustics, Speech and Signal Processing, 2017. [<a href="https://ai.google/research/pubs/pub45857">PDF</a>] [2] Eduardo Fonseca, Jordi Pons, Xavier Favory, Frederic Font, Dmitry Bogdanov, Andres Ferraro, Sergio Oramas, Alastair Porter, and Xavier Serra. "Freesound Datasets: A Platform for the Creation of Open Audio Datasets." In Proceedings of the International Conference on Music Information Retrieval, 2017. [<a href="https://repositori.upf.edu/bitstream/handle/10230/33299/fonseca_ismir17_freesound.pdf">PDF</a>] Companion site for FSD50K: <a href="https://annotator.freesound.org/fsd/release/FSD50K/">https://annotator.freesound.org/fsd/release/FSD50K/</a> Freesound Annotator: <a href="https://annotator.freesound.org/">https://annotator.freesound.org/</a> Freesound: <a href="https://freesound.org">https://freesound.org</a> Eduardo Fonseca's personal website: <a href="http://www.eduardofonseca.net/">http://www.eduardofonseca.net/</a> More datasets collected by us: <a href="http://www.eduardofonseca.net/datasets/">http://www.eduardofonseca.net/datasets/</a> ## Acknowledgments The authors would like to thank everyone who contributed to FSD50K with annotations, and especially Mercedes Collado, Ceren Can, Rachit Gupta, Javier Arredondo, Gary Avendano and Sara Fernandez for their commitment and perseverance. The authors would also like to thank Daniel P.W. Ellis and Manoj Plakal from Google Research for valuable discussions. This work is partially supported by the European Union’s Horizon 2020 research and innovation programme under grant agreement No 688382 <a href="https://www.audiocommons.org/">AudioCommons</a>, and two Google Faculty Research Awards <a href="https://ai.googleblog.com/2018/03/google-faculty-research-awards-2017.html">2017</a> and <a href="https://ai.googleblog.com/2019/03/google-faculty-research-awards-2018.html">2018</a>, and the Maria de Maeztu Units of Excellence Programme (MDM-2015-0502).

nickfuryavg/Kathbath-Audio-44100-Batch-28

nickfuryavg

2025-03-25T12:04:36Z

15

0

[ "size_categories:1K<n<10K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-03-25T12:04:21Z

0

--- dataset_info: features: - name: fname dtype: string - name: text dtype: string - name: audio_filepath dtype: audio: sampling_rate: 44100 - name: gender dtype: string splits: - name: train num_bytes: 158271555.0 num_examples: 1000 download_size: 155299101 dataset_size: 158271555.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

ZHLiu627/updated-code-qwen7-edu

ZHLiu627

2025-02-21T18:07:42Z

26

0

[ "size_categories:10K<n<100K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-02-21T18:07:35Z

0

--- dataset_info: features: - name: seq_id dtype: int64 - name: instruction dtype: string - name: output dtype: string - name: code dtype: string - name: entry_point dtype: string - name: testcase sequence: string - name: prompt dtype: string - name: new_prompt dtype: string - name: responses sequence: string - name: rewards sequence: float64 - name: mean_reward dtype: float64 splits: - name: train num_bytes: 427086591 num_examples: 75626 download_size: 148777252 dataset_size: 427086591 configs: - config_name: default data_files: - split: train path: data/train-* ---

Asap7772/safety_nofix_evalbase_vllmgen__3212_3670

Asap7772

2025-03-02T23:44:11Z

17

0

[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-03-02T23:44:00Z

0

--- dataset_info: features: - name: chat_y_w list: - name: content dtype: string - name: role dtype: string - name: chat_y_l list: - name: content dtype: string - name: role dtype: string - name: reward_yw sequence: float64 - name: reward_yl sequence: float64 - name: question_list sequence: string - name: response_yw_list sequence: string - name: response_yl_list sequence: string - name: source dtype: string - name: query dtype: string - name: completions sequence: string splits: - name: train num_bytes: 42298574 num_examples: 458 download_size: 19531732 dataset_size: 42298574 configs: - config_name: default data_files: - split: train path: data/train-* ---

avdeep/half_sanskrit_speakerembeddings

avdeep

2025-02-13T18:17:50Z

16

0

[ "size_categories:10K<n<100K", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-02-13T18:16:19Z

0

--- dataset_info: features: - name: input_ids sequence: int32 - name: labels sequence: sequence: float32 - name: speaker_embeddings sequence: float32 splits: - name: train num_bytes: 2460357452 num_examples: 18607 download_size: 2456505911 dataset_size: 2460357452 configs: - config_name: default data_files: - split: train path: data/train-* ---

Cadenza-Labs/alpaca_Mistral-Small-3.1-24B-Instruct

Cadenza-Labs

2025-05-24T12:27:33Z

14

0

[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-05-23T13:26:27Z

0

--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: dishonest dtype: bool splits: - name: train num_bytes: 7625123 num_examples: 7210 download_size: 4196413 dataset_size: 7625123 configs: - config_name: default data_files: - split: train path: data/train-* ---

cestwc/SG-subzone-poi-estate-share

cestwc

2025-01-15T23:52:37Z

53

0

[ "size_categories:1M<n<10M", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-01-15T23:52:15Z

0

--- dataset_info: features: - name: id dtype: int64 - name: text dtype: string - name: source dtype: string - name: truncated dtype: bool - name: latitude dtype: float32 - name: longitude dtype: float32 - name: year_created_at dtype: int64 - name: month_created_at dtype: int64 - name: day_created_at dtype: int64 - name: weekday_created_at dtype: int64 - name: hour_created_at dtype: int64 - name: minute_created_at dtype: int64 - name: subzone dtype: string - name: polarity_score dtype: float32 - name: label_manual dtype: int64 - name: label_T01 dtype: int64 - name: label_bart dtype: float32 - name: label_T02 dtype: int64 - name: num_keywords dtype: int64 - name: preprocess-1 dtype: string - name: preprocess-2 dtype: string - name: label_llama dtype: int64 - name: label_c dtype: bool - name: llama-2 dtype: string - name: relatedness dtype: float64 - name: label dtype: float64 - name: planning_area dtype: class_label: names: '0': '' '1': ANG MO KIO '2': BEDOK '3': BISHAN '4': BOON LAY '5': BUKIT BATOK '6': BUKIT MERAH '7': BUKIT PANJANG '8': BUKIT TIMAH '9': CENTRAL WATER CATCHMENT '10': CHANGI '11': CHOA CHU KANG '12': CLEMENTI '13': DOWNTOWN CORE '14': GEYLANG '15': HOUGANG '16': JURONG EAST '17': JURONG WEST '18': KALLANG '19': LIM CHU KANG '20': MANDAI '21': MARINA EAST '22': MARINA SOUTH '23': MARINE PARADE '24': MUSEUM '25': NEWTON '26': NORTH-EASTERN ISLANDS '27': NOVENA '28': ORCHARD '29': OUTRAM '30': PASIR RIS '31': PAYA LEBAR '32': PIONEER '33': PUNGGOL '34': QUEENSTOWN '35': RIVER VALLEY '36': ROCHOR '37': SELETAR '38': SEMBAWANG '39': SENGKANG '40': SERANGOON '41': SIMPANG '42': SINGAPORE RIVER '43': SOUTHERN ISLANDS '44': STRAITS VIEW '45': SUNGEI KADUT '46': TAMPINES '47': TANGLIN '48': TENGAH '49': TOA PAYOH '50': TUAS '51': WESTERN ISLANDS '52': WESTERN WATER CATCHMENT '53': WOODLANDS '54': YISHUN - name: category dtype: class_label: names: '0': Animals and Birds '1': Cleanliness '2': Connectivity Related Infrastructure '3': Enforcement Matters '4': General Infrastructure/Facilities '5': Greenery '6': Illegal Parking '7': Neighbour Issues '8': Noise '9': Pests '10': Pollution '11': Public Housing Infrastructure (Excl Lifts) '12': Public Housing Lifts '13': '' splits: - name: train num_bytes: 1011861795 num_examples: 1025135 download_size: 321895097 dataset_size: 1011861795 configs: - config_name: default data_files: - split: train path: data/train-* ---

1231czx/rlhflow_mix_w_dart_math

1231czx

2024-10-18T15:25:22Z

21

0

[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2024-10-18T15:23:36Z

0

--- dataset_info: features: - name: conversations list: - name: content dtype: string - name: role dtype: string - name: source dtype: string - name: conversation_id dtype: int64 splits: - name: train num_bytes: 2793967415.7409267 num_examples: 1831548 download_size: 1367201281 dataset_size: 2793967415.7409267 configs: - config_name: default data_files: - split: train path: data/train-* ---

mlfoundations-dev/oh_teknium_scaling_down_random_1.0

mlfoundations-dev

2024-12-21T13:21:40Z

14

0

[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2024-12-21T13:21:12Z

0

--- dataset_info: features: - name: conversations list: - name: from dtype: string - name: value dtype: string - name: weight dtype: float64 splits: - name: train num_bytes: 1605295072 num_examples: 1001551 download_size: 779986988 dataset_size: 1605295072 configs: - config_name: default data_files: - split: train path: data/train-* ---

ZixuanKe/cfa_extracted_exercise_sup_sample_from_policy_v1_1_rpo_iter_1_dpo_binarized_val_chunk_5

ZixuanKe

2024-11-16T06:45:34Z

19

0

[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2024-11-16T06:45:33Z

0

--- dataset_info: features: - name: prompt dtype: string - name: rejected dtype: string - name: chosen dtype: string splits: - name: train num_bytes: 7156 num_examples: 6 download_size: 12097 dataset_size: 7156 configs: - config_name: default data_files: - split: train path: data/train-* ---

fhai50032/Math-Pretrain-Packed-QTK-81K

fhai50032

2025-03-10T15:43:31Z

15

1

[ "size_categories:1M<n<10M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-03-10T15:39:13Z

0

--- dataset_info: features: - name: input_ids sequence: int32 - name: attention_mask sequence: int8 splits: - name: train num_bytes: 18755356704 num_examples: 1830148 download_size: 5894246453 dataset_size: 18755356704 configs: - config_name: default data_files: - split: train path: data/train-* ---

kadirnar/combined-turkish-dataset-v5-unsloth

kadirnar

2025-04-02T22:21:55Z

18

0

[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-04-02T18:02:58Z

0

--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 1464850790 num_examples: 1054470 download_size: 770824035 dataset_size: 1464850790 configs: - config_name: default data_files: - split: train path: data/train-* ---

mandanya/logseq-query-clojure

mandanya

2024-11-27T11:07:44Z

17

0

[ "license:apache-2.0", "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2024-11-27T05:08:36Z

0

--- license: apache-2.0 dataset_info: features: - name: prompt dtype: string - name: query dtype: string - name: synthetic dtype: int64 - name: orig_index dtype: float64 splits: - name: train num_bytes: 385651 num_examples: 801 - name: test num_bytes: 40982 num_examples: 81 download_size: 89211 dataset_size: 426633 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

JesusCrist/mt_bench_prompts

JesusCrist

2025-05-28T06:38:29Z

0

[ "license:mit", "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-05-28T05:54:42Z

0

--- license: mit configs: - config_name: default data_files: - split: train path: data/train-* dataset_info: features: - name: question_id dtype: int64 - name: category dtype: string - name: turns sequence: string - name: reference sequence: string - name: gpt4_reference sequence: string splits: - name: train num_bytes: 91373 num_examples: 80 download_size: 53582 dataset_size: 91373 ---

masaki-sakata/wikidata_descriptions

masaki-sakata

2025-05-21T13:58:01Z

0

[ "language:en", "license:mit", "region:us", "Wikidata", "Wikipedia", "Description", "Entity", "QID", "Knowledge" ]

[]

2025-05-21T13:30:44Z

0

--- dataset_info: features: - name: wiki_title dtype: string - name: qid dtype: string - name: description dtype: string splits: - name: en num_bytes: 1938197 num_examples: 26205 download_size: 1256160 dataset_size: 1938197 configs: - config_name: default data_files: - split: en path: data/en-* license: mit language: - en tags: - Wikidata - Wikipedia - Description - Entity - QID - Knowledge --- # Wikidata Descriptions Dataset `wikidata_descriptions` pairs English Wikipedia article titles (`wiki_title`) and their Wikidata IDs (`qid`) with the **English "description"** available in Wikidata. The corpus contains **26 205 entities**. Wikidata descriptions are short, one-line summaries that concisely state what an entity is. They can be used as lightweight contextual information in entity linking, search, question answering, knowledge-graph completion and many other NLP / IR tasks. --- ## Dataset Structure ```python from datasets import load_dataset ds = load_dataset("masaki-sakata/wikidata_descriptions", split="en") print(ds) # Dataset({ # features: ['wiki_title', 'qid', 'description'], # num_rows: 26205 # }) ``` Field description: | column | type | description | |--------------|--------|--------------------------------------------------------------------| | `wiki_title` | str | Title of the corresponding English Wikipedia article | | `qid` | str | Wikidata identifier, e.g. `Q7156` | | `description`| str | English one-line description provided by Wikidata (CC-0) | Example: ```json { "wiki_title": "Michael Jordan", "qid": "Q41421", "description": "American basketball player and businessman (born 1963)" } ``` ## Quick Usage Example ```python from datasets import load_dataset ds = load_dataset("masaki-sakata/wikidata_descriptions", split="en") # Retrieve the first 3 entities for record in ds.select(range(3)): print(record) ``` --- ## Source & Construction 1. **Seed list** [`masaki-sakata/entity_popularity`](https://huggingface.co/datasets/masaki-sakata/entity_popularity) (English split) provides `wiki_title` and `qid`. 2. **Enrichment** For every `qid`, we queried the Wikidata API (`wbgetentities`, language = `en`) and kept the English description if present. 3. **Filtering** Rows with empty or missing descriptions were dropped, resulting in 26 205 items. 4. **License** All descriptions originate from Wikidata and are released under CC-0. The dataset as a whole is distributed under the MIT License. ---

lianghsun/Everything-Instruct-Multilingual-DPO

lianghsun

2024-12-10T01:06:43Z

76

1

[ "language:en", "language:ru", "language:zh", "language:ko", "language:ur", "language:la", "language:ar", "language:de", "language:es", "language:fr", "language:hi", "language:it", "language:ja", "language:nl", "language:pt", "license:cc-by-nc-sa-4.0", "size_categories:1M<n<10M", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2305.18290", "region:us", "sft", "dpo" ]

[]

2024-12-05T01:37:25Z

0

--- license: cc-by-nc-sa-4.0 language: - en - ru - zh - ko - ur - la - ar - de - es - fr - hi - it - ja - nl - pt tags: - sft - dpo size_categories: - 1M<n<10M --- # Dataset Card for lianghsun/Everything-Instruct-Multilingual-DPO  ## Dataset Details ### Dataset Description  這個資料集是分叉於 [rombodawg/Everything_Instruct_Multilingual](https://huggingface.co/datasets/rombodawg/Everything_Instruct_Multilingual)，但在中文回答的部份透過 [opencc-python](https://github.com/yichen0831/opencc-python) 將簡體中文（zh-cn）轉成繁體中文（zh-tw）。除此之外，我們將資料集升級成具有 [DPO](https://arxiv.org/abs/2305.18290) 欄位，該 `rejected` 回覆是由 [lianghsun/Llama-3.2-Taiwan-3B-Instruct](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B-Instruct) `v2024.11.27` 生成，此資料集將用於 lianghsun/Llama-3.2-Taiwan-3B-Instruct 的 DPO 階段。 - **Curated by:** [Huang Liang Hsun](https://www.linkedin.com/in/lianghsunhuang/?locale=en_US) - **Language(s) (NLP):** multilingual - **License:** cc-by-nc-sa-4.0 ### Dataset Sources  - **Repository:** [lianghsun/Everything-Instruct-Multilingual](https://huggingface.co/datasets/lianghsun/Everything-Instruct-Multilingual/) ## Uses  ### Direct Use  本資料集可以用在 SFT 與 DPO 的訓練階段。 ### Out-of-Scope Use  本資料集並不適合用在評測集或者是任何事實審核使用。 ## Dataset Structure  ```yaml { "instruction": "", "input": "", "rejected": "" } ``` ## Dataset Creation ### Curation Rationale  具有多國語系的指令資料集鮮少，更不用說多國語系的偏好資料集（Preference dataset），故本資料集以 [rombodawg/Everything_Instruct_Multilingual](https://huggingface.co/datasets/rombodawg/Everything_Instruct_Multilingual) 為基底資料集（foundation dataset），新增拒絕（rejected）回覆，使資料集更加全面，用戶可利用此資料集訓練模型進行多語系偏好學習。 ### Source Data  #### Data Collection and Processing  1. **簡體中文轉繁體中文：** 本資料集將簡體中文轉成繁體中文。 2. **生成拒絕回覆：** 透過模型生成拒絕回覆，以建立偏好資料集。 #### Who are the source data producers?  - **Foundation dataset:** [rombodawg/Everything_Instruct_Multilingual](https://huggingface.co/datasets/rombodawg/Everything_Instruct_Multilingual) - **Rejected dataset:** [lianghsun/Llama-3.2-Taiwan-3B-Instruct](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B-Instruct) ### Annotations [optional]  #### Annotation process  無。 #### Who are the annotators?  無。 #### Personal and Sensitive Information  我們未針對原始資料進行 PII 檢測，但曾經收過 Hugging Face 系統信通知原始資料集內含有密鑰相關，請使用者再自行檢測。 ## Bias, Risks, and Limitations  任何人使用此資料集都應該要注意，原始資料內可能含有不同立場和情境的言論，請小心使用。 ### Recommendations  Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations. ## Citation [optional]  ```yaml @misc{huang2024everything, author = {Huang, Liang Hsun}, title = {Everything-Instruct-Multilingual-DPO}, year = {2024}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/datasets/lianghsun/Everything-Instruct-Multilingual-DPO}}, note = {多國語系的指令服從資料集，可用於 SFT 或 DPO 訓練} } ``` ## More Information 本人僅能檢視繁體中文的部分，原始資料集含有中文的部分，大部分都是被要求翻譯成為中文（output），但經檢視中文的文本品質並不是很高水準，更甚至可能原始產生輸出的模型之中文能力低落，建議可以將有中文輸出的欄位刪除後再進行訓練。 *註：至此至今，我開始也懷疑原始資料集的多國語系指令回覆，是否也是低品質？* 但如果你缺少一個多國語系的指令資料集，這將是一個很好入門的資料集。 ## Dataset Card Authors [Huang Liang Hsun](https://www.linkedin.com/in/lianghsunhuang/?locale=en_US) ## Dataset Card Contact [Huang Liang Hsun](https://www.linkedin.com/in/lianghsunhuang/?locale=en_US)

abar-uwc/vaani-bihar_saharsa-cleaned

abar-uwc

2025-05-29T09:50:56Z

42

0

[ "size_categories:1K<n<10K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-05-29T09:50:27Z

0

--- dataset_info: features: - name: audio dtype: audio - name: language dtype: string - name: languagesKnown dtype: string - name: gender dtype: string - name: state dtype: string - name: district dtype: string - name: pincode dtype: int64 - name: stay(years) dtype: string - name: isTranscriptionAvailable dtype: string - name: transcript dtype: string - name: referenceImage dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 966513063.93 num_examples: 4701 download_size: 949827251 dataset_size: 966513063.93 configs: - config_name: default data_files: - split: train path: data/train-* ---

HanyangMed/final_diagnosis_medqa

HanyangMed

2025-02-16T17:34:35Z

22

0

[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-02-15T08:46:43Z

0

--- dataset_info: features: - name: question dtype: string - name: options dtype: string - name: answer dtype: string - name: meta_info dtype: string - name: answer_idx dtype: string splits: - name: train num_bytes: 2056320.318769505 num_examples: 3658 - name: test num_bytes: 229019.69477911646 num_examples: 416 download_size: 1487566 dataset_size: 2285340.0135486214 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

BarryFutureman/vpt_data_8xx_shard0214

BarryFutureman

2025-06-11T02:26:04Z

0

[ "task_categories:robotics", "license:apache-2.0", "size_categories:10K<n<100K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us", "LeRobot" ]

[ "robotics" ]

2025-06-11T02:24:32Z

0

--- license: apache-2.0 task_categories: - robotics tags: - LeRobot configs: - config_name: default data_files: data/*/*.parquet --- This dataset was created using [LeRobot](https://github.com/huggingface/lerobot). ## Dataset Description - **Homepage:** [More Information Needed] - **Paper:** [More Information Needed] - **License:** apache-2.0 ## Dataset Structure [meta/info.json](meta/info.json): ```json { "codebase_version": "v2.1", "robot_type": null, "total_episodes": 10, "total_frames": 42289, "total_tasks": 1, "total_videos": 0, "total_chunks": 1, "chunks_size": 1000, "fps": 20, "splits": { "train": "0:10" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4", "features": { "observation.image": { "dtype": "image", "shape": [ 3, 360, 640 ], "names": [ "channel", "height", "width" ] }, "action": { "dtype": "string", "shape": [ 1 ], "names": null }, "timestamp": { "dtype": "float32", "shape": [ 1 ], "names": null }, "frame_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "episode_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "task_index": { "dtype": "int64", "shape": [ 1 ], "names": null } } } ``` ## Citation **BibTeX:** ```bibtex [More Information Needed] ```

marco-schouten/1_shape

marco-schouten

2024-11-28T15:05:19Z

15

0

[ "size_categories:n<1K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2024-11-28T14:57:26Z

0

--- dataset_info: features: - name: input_image dtype: image - name: edit_prompt dtype: string - name: edited_image dtype: image splits: - name: train num_bytes: 100968.0 num_examples: 27 download_size: 50708 dataset_size: 100968.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

yvan-pimi/swahili-child-assessment

yvan-pimi

2025-06-10T12:05:13Z

63

0

[ "size_categories:n<1K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]

[]

2025-06-10T12:05:05Z

0

--- dataset_info: features: - name: audio dtype: audio: sampling_rate: 16000 - name: sr dtype: int64 - name: grade-level dtype: int64 - name: wpm dtype: int64 - name: acc dtype: int64 - name: grade dtype: int64 - name: mistakes dtype: int64 - name: sentence dtype: string splits: - name: train num_bytes: 25860353.0 num_examples: 75 download_size: 19737032 dataset_size: 25860353.0 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "swahili-child-assessment" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

Datasets:

librarian-bots
/

dataset_cards_with_metadata

Dataset Card for Hugging Face Hub Dataset Cards

Dataset Details

Uses

Out-of-Scope Use

Dataset Structure

Dataset Creation

Curation Rationale

Source Data

Data Collection and Processing

Who are the source data producers?

Annotations [optional]

Annotation process

Who are the annotators?

Personal and Sensitive Information

Bias, Risks, and Limitations

Recommendations

Citation

Dataset Card Authors

Dataset Card Contact

Space using librarian-bots/dataset_cards_with_metadata 1

Collection including librarian-bots/dataset_cards_with_metadata

Hub Card Data