Datasets:

---

ftopal

/

huggingface-datasets

like 0

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"AI-generated-inpaintings-dataset\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"AI-generated-inpaintings-dataset\"\n\nMore Information needed" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[ "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n", "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "size_categories:10K<n<100K", "language:en", "language:es", "language:ru", "language:de", "language:pl", "language:th", "language:vi", "language:sv", "language:bn", "language:da", "language:he", "language:it", "language:fa", "language:sk", "language:id", "language:nb", "language:el", "language:nl", "language:hu", "language:eu", "language:zh", "language:eo", "language:ja", "language:ca", "language:cs", "language:bg", "language:fi", "language:pt", "language:tr", "language:ro", "language:ar", "language:uk", "language:gl", "language:fr", "language:ko", "license:apache-2.0", "human-feedback", "region:us" ]

[]

[ "en", "es", "ru", "de", "pl", "th", "vi", "sv", "bn", "da", "he", "it", "fa", "sk", "id", "nb", "el", "nl", "hu", "eu", "zh", "eo", "ja", "ca", "cs", "bg", "fi", "pt", "tr", "ro", "ar", "uk", "gl", "fr", "ko" ]

[]

[ "TAGS\n#size_categories-10K<n<100K #language-English #language-Spanish #language-Russian #language-German #language-Polish #language-Thai #language-Vietnamese #language-Swedish #language-Bengali #language-Danish #language-Hebrew #language-Italian #language-Persian #language-Slovak #language-Indonesian #language-Norwegian Bokmål #language-Modern Greek (1453-) #language-Dutch #language-Hungarian #language-Basque #language-Chinese #language-Esperanto #language-Japanese #language-Catalan #language-Czech #language-Bulgarian #language-Finnish #language-Portuguese #language-Turkish #language-Romanian #language-Arabic #language-Ukrainian #language-Galician #language-French #language-Korean #license-apache-2.0 #human-feedback #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"jeopardy\"\n\nThis is a processed version of the original jeopardy dataset.\n\nThe 'test' split contains all the jeopardy questions in the following categories:\n- american_history\n- world_history\n- literature\n- science\n- word_origins\n\nThe 'train' split contains all the jeopardy questions from the remaining categories." ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"jeopardy\"\n\nThis is a processed version of the original jeopardy dataset.\n\nThe 'test' split contains all the jeopardy questions in the following categories:\n- american_history\n- world_history\n- literature\n- science\n- word_origins\n\nThe 'train' split contains all the jeopardy questions from the remaining categories." ]

[ "annotations_creators:no-annotation", "language_creators:found", "multilinguality:monolingual", "size_categories:1M<n<10M", "language:en", "license:cc-by-sa-3.0", "license:gfdl", "pretraining", "language modelling", "wikipedia", "web", "region:us" ]

[]

[ "en" ]

[ "# Dataset Card for Wikipedia English January 2024\n\nDataset created using this repo with a January 2024 Wikipedia snapshot.\n\nThis repo also has a precomputed pageviews database. This database has the aggregated number of views for each page in Wikipedia. This file is built using the Wikipedia Pageview complete dumps" ]

[ "TAGS\n#annotations_creators-no-annotation #language_creators-found #multilinguality-monolingual #size_categories-1M<n<10M #language-English #license-cc-by-sa-3.0 #license-gfdl #pretraining #language modelling #wikipedia #web #region-us \n", "# Dataset Card for Wikipedia English January 2024\n\nDataset created using this repo with a January 2024 Wikipedia snapshot.\n\nThis repo also has a precomputed pageviews database. This database has the aggregated number of views for each page in Wikipedia. This file is built using the Wikipedia Pageview complete dumps" ]

[ "task_categories:question-answering", "task_categories:text-generation", "task_categories:conversational", "size_categories:1K<n<10K", "language:en", "license:apache-2.0", "hypnosis", "therapy", "mental health", "region:us" ]

[]

[ "en" ]

[ "# dataset card for \"hypnosis_dataset\"", "##### hypnosis scripts based on Erickson progressions\n\n\n\nThis is a small dataset containing hypnosis scripts that were both obtained from legitimate (manual) sources, and also generated using the following closed and open models:\nlarge llm:\n- openai api\n- cohere\n- palm\nopen models:\n- mistral-7b\n- trismegistus-mistral-7b\n- zephyr-7b\n- mistral-anima-phi-7b\n- mistral-instruct\n\nThe data has been cleaned but not altered save for formatting. \nSome entries include a large, unsupervised text blob for training semantics and pattern flow.\nSome repetition is present - future versions will work on enhanced cleaning and filtering, as well as additional generation using different model types that produce interesting scripts." ]

[ "TAGS\n#task_categories-question-answering #task_categories-text-generation #task_categories-conversational #size_categories-1K<n<10K #language-English #license-apache-2.0 #hypnosis #therapy #mental health #region-us \n", "# dataset card for \"hypnosis_dataset\"", "##### hypnosis scripts based on Erickson progressions\n\n\n\nThis is a small dataset containing hypnosis scripts that were both obtained from legitimate (manual) sources, and also generated using the following closed and open models:\nlarge llm:\n- openai api\n- cohere\n- palm\nopen models:\n- mistral-7b\n- trismegistus-mistral-7b\n- zephyr-7b\n- mistral-anima-phi-7b\n- mistral-instruct\n\nThe data has been cleaned but not altered save for formatting. \nSome entries include a large, unsupervised text blob for training semantics and pattern flow.\nSome repetition is present - future versions will work on enhanced cleaning and filtering, as well as additional generation using different model types that produce interesting scripts." ]

[ "task_categories:text-classification", "size_categories:10K<n<100K", "language:en", "license:cc", "toxicity", "region:us" ]

[]

[ "en" ]

[ "# Tweets", "## Overview \n\nThis dataset contains texts from customers posted on Twitter regarding their air travel experiences,\nwhether they were upset, neutral, or satisfied with the trip and the airline's service.", "## Dataset Details\n\nThe dataset is a smaller version of the original datase. This data originally came from Crowdflower's Data for Everyone library\n The original Twitter data was scraped from February 2015, and contributors were asked first to classify positive, negative, and neutral tweets,\nfollowed by categorizing negative reasons (such as \"late flight\" or \"rude service\").\nThis version contains whether the sentiment of the tweets in this set was positive (16%), neutral (21%), or negative (63%) for six US airlines.\n\n- Dataset Name: Twitter US Airline Sentiment\n- Language: English\n- Total Size: 14,640 demonstrations", "## Contents\n\nThe dataset consists of a data frame with the following columns:\n\n- label\n- text", "## How to use", "## License\n\nThe Twitter US Airline Sentiment is licensed under the Creative Commons(CC) License CC BY-NC-SA 4.0." ]

[ "TAGS\n#task_categories-text-classification #size_categories-10K<n<100K #language-English #license-cc #toxicity #region-us \n", "# Tweets", "## Overview \n\nThis dataset contains texts from customers posted on Twitter regarding their air travel experiences,\nwhether they were upset, neutral, or satisfied with the trip and the airline's service.", "## Dataset Details\n\nThe dataset is a smaller version of the original datase. This data originally came from Crowdflower's Data for Everyone library\n The original Twitter data was scraped from February 2015, and contributors were asked first to classify positive, negative, and neutral tweets,\nfollowed by categorizing negative reasons (such as \"late flight\" or \"rude service\").\nThis version contains whether the sentiment of the tweets in this set was positive (16%), neutral (21%), or negative (63%) for six US airlines.\n\n- Dataset Name: Twitter US Airline Sentiment\n- Language: English\n- Total Size: 14,640 demonstrations", "## Contents\n\nThe dataset consists of a data frame with the following columns:\n\n- label\n- text", "## How to use", "## License\n\nThe Twitter US Airline Sentiment is licensed under the Creative Commons(CC) License CC BY-NC-SA 4.0." ]

[ "license:other", "region:us" ]

[]

[]

[ "# GUM Corpus V9.2.0\n\n- Project: URL\n- Data source: URL", "## Details\n\nAn English corpus annotated for coreference and other linguistic phenomenon. See the project repo for full corpora license information. Annotations are licensed under CC-BY-4.0.", "## Features" ]

[ "TAGS\n#license-other #region-us \n", "# GUM Corpus V9.2.0\n\n- Project: URL\n- Data source: URL", "## Details\n\nAn English corpus annotated for coreference and other linguistic phenomenon. See the project repo for full corpora license information. Annotations are licensed under CC-BY-4.0.", "## Features" ]

[ "task_categories:text-generation", "language:en", "license:apache-2.0", "region:us" ]

[]

[ "en" ]

[ "# Dataset Card for kz919/open-orca-flan-50k-synthetic-reward-e5-mistral-7b-instruct", "## Dataset Description\n\nThis data is based on kz919/open-orca-flan-50k-synthetic-5-models. intfloat/e5-mistral-7b-instruct is used to generate the router label.", "### Dataset Info\n\nThe dataset comprises the following features:\n\n1. prompt: (string) - The initial prompt or query.\n2. completion: (string) - The completed text or response.\n3. task: (string) - Description of the task.\n4. ignos-Mistral-T5-7B-v1: (string) - Responses from the ignos-Mistral-T5-7B-v1 model.\n5. cognAI-lil-c3po: (string) - Responses from the cognAI-lil-c3po model.\n6. viethq188-Rabbit-7B-DPO-Chat: (string) - Responses from the viethq188-Rabbit-7B-DPO-Chat model.\n7. cookinai-DonutLM-v1: (string) - Responses from the cookinai-DonutLM-v1 model.\n8. v1olet-v1olet-merged-dpo-7B: (string) - Responses from the v1olet-v1olet-merged-dpo-7B model.\n9. normalized_rewards: (sequence of float32) - Normalized reward scores.\n10. router_label: (int64) - Router labels.", "### Splits\n\n- Train: \n - num_bytes: 105157970\n - num_examples: 50000", "### Size\n\n- Download Size: 48532376\n- Dataset Size: 105157970", "## Configurations\n\n- Config Name: default\n- Data Files:\n - Train:\n - Path: data/train-*", "## Task Categories\n\n- Text Generation", "## Language\n\n- English (en)" ]

[ "TAGS\n#task_categories-text-generation #language-English #license-apache-2.0 #region-us \n", "# Dataset Card for kz919/open-orca-flan-50k-synthetic-reward-e5-mistral-7b-instruct", "## Dataset Description\n\nThis data is based on kz919/open-orca-flan-50k-synthetic-5-models. intfloat/e5-mistral-7b-instruct is used to generate the router label.", "### Dataset Info\n\nThe dataset comprises the following features:\n\n1. prompt: (string) - The initial prompt or query.\n2. completion: (string) - The completed text or response.\n3. task: (string) - Description of the task.\n4. ignos-Mistral-T5-7B-v1: (string) - Responses from the ignos-Mistral-T5-7B-v1 model.\n5. cognAI-lil-c3po: (string) - Responses from the cognAI-lil-c3po model.\n6. viethq188-Rabbit-7B-DPO-Chat: (string) - Responses from the viethq188-Rabbit-7B-DPO-Chat model.\n7. cookinai-DonutLM-v1: (string) - Responses from the cookinai-DonutLM-v1 model.\n8. v1olet-v1olet-merged-dpo-7B: (string) - Responses from the v1olet-v1olet-merged-dpo-7B model.\n9. normalized_rewards: (sequence of float32) - Normalized reward scores.\n10. router_label: (int64) - Router labels.", "### Splits\n\n- Train: \n - num_bytes: 105157970\n - num_examples: 50000", "### Size\n\n- Download Size: 48532376\n- Dataset Size: 105157970", "## Configurations\n\n- Config Name: default\n- Data Files:\n - Train:\n - Path: data/train-*", "## Task Categories\n\n- Text Generation", "## Language\n\n- English (en)" ]

[ "license:other", "region:us" ]

[]

[]

[ "# CorefUD v1.1\n\n- Project: URL\n- Data source: URL", "## Details\n\nFrom URL\n\nCorefUD is a collection of previously existing datasets annotated with coreference, which we converted into a common annotation scheme. In total, CorefUD in its current version 1.1 consists of 21 datasets for 13 languages. The datasets are enriched with automatic morphological and syntactic annotations that are fully compliant with the standards of the Universal Dependencies project. All the datasets are stored in the CoNLL-U format, with coreference- and bridging-specific information captured by attribute-value pairs located in the MISC column. The collection is divided into a public edition and a non-public (ÚFAL-internal) edition. The publicly available edition is distributed via LINDAT-CLARIAH-CZ and contains 17 datasets for 12 languages (1 dataset for Catalan, 2 for Czech, 2 for English, 1 for French, 2 for German, 2 for Hungarian, 1 for Lithuanian, 2 for Norwegian, 1 for Polish, 1 for Russian, 1 for Spanish, and 1 for Turkish), excluding the test data. The non-public edition is available internally to ÚFAL members and contains additional 4 datasets for 2 languages (1 dataset for Dutch, and 3 for English), which we are not allowed to distribute due to their original license limitations. It also contains the test data portions for all datasets. When using any of the harmonized datasets, please get acquainted with its license (placed in the same directory as the data) and cite the original data resource too. Compared to the previous version 1.0, the version 1.1 comprises new languages and corpora, namely Hungarian-KorKor, Norwegian-BokmaalNARC, Norwegian-NynorskNARC, and Turkish-ITCC. In addition, the English GUM dataset has been updated to a newer and larger version, and the conversion pipelines for most datasets have been refined (a list of all changes in each dataset can be found in the corresponding README file).", "## Licenses\n\n1. Catalan-AnCora: The treebank is licensed under the Creative Commons License Attribution 4.0 International. The complete license text is available at:\nURL\n1. Czech-PCEDT: Attribution-NonCommercial-ShareAlike 3.0 Unported\n1. Czech-PDT: Attribution-NonCommercial-ShareAlike 4.0 International\n1. GUM: Anootations are Creative Commons Attribution (CC-BY) version 4.0 Note: reddit data is excluded from CorefUD due to licensing:\n 1. Wikinews/interviews: URL (Source: URL\n 1. WikiVoyage: URL (Source: URL\n 1. WikiHow: URL (Source: URL\n 1. Academic: Multiple sources, all URL\n 1. Biographies: URL (Source: URL\n 1. Fiction: URL (Source: URL\n1. English-ParCorFull: Attribution-NonCommercial 4.0 International\n1. French-Democrat: Attribution-ShareAlike 4.0 International\n1. German-ParCorFull: Attribution-NonCommercial 4.0 International\n1. German-PotsdamCC: Attribution-NonCommercial-ShareAlike 4.0 International\n1. Hungarian-KorKor: Creative Commons Attribution 4.0 International Public License\n1. Hungarian-SzegedKoref: Attribution 4.0 International\n1. Lithuanian-LCC: CLARIN-LT PUBLIC END-USER LICENCE (PUB)\n1. Norwegian-BokmaaINARC: Attribution-ShareAlike 4.0 International\n1. Norwegian-NynorskNARC: Attribution-ShareAlike 4.0 International\n1. Polish-PCC: CC Attribution 3.0 Unported\n1. Russian-RuCor: Attribution-ShareAlike 4.0 International\n1. Spanish-AnCora: Creative Commons License Attribution 4.0 International\n1. Turkish-ITCC: Attribution-NonCommercial-ShareAlike 4.0 International" ]

[ "TAGS\n#license-other #region-us \n", "# CorefUD v1.1\n\n- Project: URL\n- Data source: URL", "## Details\n\nFrom URL\n\nCorefUD is a collection of previously existing datasets annotated with coreference, which we converted into a common annotation scheme. In total, CorefUD in its current version 1.1 consists of 21 datasets for 13 languages. The datasets are enriched with automatic morphological and syntactic annotations that are fully compliant with the standards of the Universal Dependencies project. All the datasets are stored in the CoNLL-U format, with coreference- and bridging-specific information captured by attribute-value pairs located in the MISC column. The collection is divided into a public edition and a non-public (ÚFAL-internal) edition. The publicly available edition is distributed via LINDAT-CLARIAH-CZ and contains 17 datasets for 12 languages (1 dataset for Catalan, 2 for Czech, 2 for English, 1 for French, 2 for German, 2 for Hungarian, 1 for Lithuanian, 2 for Norwegian, 1 for Polish, 1 for Russian, 1 for Spanish, and 1 for Turkish), excluding the test data. The non-public edition is available internally to ÚFAL members and contains additional 4 datasets for 2 languages (1 dataset for Dutch, and 3 for English), which we are not allowed to distribute due to their original license limitations. It also contains the test data portions for all datasets. When using any of the harmonized datasets, please get acquainted with its license (placed in the same directory as the data) and cite the original data resource too. Compared to the previous version 1.0, the version 1.1 comprises new languages and corpora, namely Hungarian-KorKor, Norwegian-BokmaalNARC, Norwegian-NynorskNARC, and Turkish-ITCC. In addition, the English GUM dataset has been updated to a newer and larger version, and the conversion pipelines for most datasets have been refined (a list of all changes in each dataset can be found in the corresponding README file).", "## Licenses\n\n1. Catalan-AnCora: The treebank is licensed under the Creative Commons License Attribution 4.0 International. The complete license text is available at:\nURL\n1. Czech-PCEDT: Attribution-NonCommercial-ShareAlike 3.0 Unported\n1. Czech-PDT: Attribution-NonCommercial-ShareAlike 4.0 International\n1. GUM: Anootations are Creative Commons Attribution (CC-BY) version 4.0 Note: reddit data is excluded from CorefUD due to licensing:\n 1. Wikinews/interviews: URL (Source: URL\n 1. WikiVoyage: URL (Source: URL\n 1. WikiHow: URL (Source: URL\n 1. Academic: Multiple sources, all URL\n 1. Biographies: URL (Source: URL\n 1. Fiction: URL (Source: URL\n1. English-ParCorFull: Attribution-NonCommercial 4.0 International\n1. French-Democrat: Attribution-ShareAlike 4.0 International\n1. German-ParCorFull: Attribution-NonCommercial 4.0 International\n1. German-PotsdamCC: Attribution-NonCommercial-ShareAlike 4.0 International\n1. Hungarian-KorKor: Creative Commons Attribution 4.0 International Public License\n1. Hungarian-SzegedKoref: Attribution 4.0 International\n1. Lithuanian-LCC: CLARIN-LT PUBLIC END-USER LICENCE (PUB)\n1. Norwegian-BokmaaINARC: Attribution-ShareAlike 4.0 International\n1. Norwegian-NynorskNARC: Attribution-ShareAlike 4.0 International\n1. Polish-PCC: CC Attribution 3.0 Unported\n1. Russian-RuCor: Attribution-ShareAlike 4.0 International\n1. Spanish-AnCora: Creative Commons License Attribution 4.0 International\n1. Turkish-ITCC: Attribution-NonCommercial-ShareAlike 4.0 International" ]

[ "task_categories:audio-classification", "size_categories:1M<n<10M", "language:en", "language:ru", "language:es", "language:pt", "language:fr", "language:ar", "language:it", "language:de", "language:tr", "language:nl", "language:ko", "license:cc-by-nc-sa-4.0", "region:us" ]

[]

[ "en", "ru", "es", "pt", "fr", "ar", "it", "de", "tr", "nl", "ko" ]

[ "### Data Instances\n\n\nA typical data point comprises the audio signal iself, with additional labels like speaker id / session id (*video\\_id*) / language / gender etc.", "### Data Fields\n\n\n* channel\\_id: YouTube channel ID from which speaker ID ('spk\\_id') is derived.\n* video\\_id: YouTube video ID, or session for speaker.\n* segment\\_id: ID of chunk of video's audio, that passed filtration process.\n* upload\\_date: Date time object representing the date when video was uploaded to YouTube.\n* language: Language of the channel / speaker.\n* gender: Gender of the channel / speaker.\n* spk\\_id: Infered integer speaker ID from channel\\_id.\n* spk\\_estim\\_age: Label of speaker age (not accurate) based on voice-based automatic age estimation & calibrated based on the upload\\_date of all videos for a given channel.\n* spk\\_estim\\_age\\_mae: MAE of spk\\_estim\\_age (might be considered as confidence).\n* audio: audio signal of a 4 seconds *mp3* segment from channel\\_id/video\\_id\n\n\nDataset description\n-------------------", "### Main statistics", "### Language and gender distributions\n\n\n!Distributions\n\n\nLanguage and gender labels of each speaker are available in original repo here.\n\n\nLicense\n-------\n\n\nThe dataset is licensed under CC BY-NC-SA 4.0, please see the complete version of the license.\n\n\nPlease also note that the provided metadata is relevant on the February 2023 and the corresponding CC BY 4.0 video licenses are valid on that date. ID R&D Inc. is not responsible for changed video license type or if the video was deleted from the YouTube platform. If you want your channel meta to be deleted from the dataset, please contact ID R&D Inc. with a topic *\"VoxTube change request\"*.\n\n\nDevelopment\n-----------\n\n\nOfficial repository live repository for opening issues.\n\n\nPlease cite the paper below if you make use of the dataset:\n\n\n''''" ]

[ "TAGS\n#task_categories-audio-classification #size_categories-1M<n<10M #language-English #language-Russian #language-Spanish #language-Portuguese #language-French #language-Arabic #language-Italian #language-German #language-Turkish #language-Dutch #language-Korean #license-cc-by-nc-sa-4.0 #region-us \n", "### Data Instances\n\n\nA typical data point comprises the audio signal iself, with additional labels like speaker id / session id (*video\\_id*) / language / gender etc.", "### Data Fields\n\n\n* channel\\_id: YouTube channel ID from which speaker ID ('spk\\_id') is derived.\n* video\\_id: YouTube video ID, or session for speaker.\n* segment\\_id: ID of chunk of video's audio, that passed filtration process.\n* upload\\_date: Date time object representing the date when video was uploaded to YouTube.\n* language: Language of the channel / speaker.\n* gender: Gender of the channel / speaker.\n* spk\\_id: Infered integer speaker ID from channel\\_id.\n* spk\\_estim\\_age: Label of speaker age (not accurate) based on voice-based automatic age estimation & calibrated based on the upload\\_date of all videos for a given channel.\n* spk\\_estim\\_age\\_mae: MAE of spk\\_estim\\_age (might be considered as confidence).\n* audio: audio signal of a 4 seconds *mp3* segment from channel\\_id/video\\_id\n\n\nDataset description\n-------------------", "### Main statistics", "### Language and gender distributions\n\n\n!Distributions\n\n\nLanguage and gender labels of each speaker are available in original repo here.\n\n\nLicense\n-------\n\n\nThe dataset is licensed under CC BY-NC-SA 4.0, please see the complete version of the license.\n\n\nPlease also note that the provided metadata is relevant on the February 2023 and the corresponding CC BY 4.0 video licenses are valid on that date. ID R&D Inc. is not responsible for changed video license type or if the video was deleted from the YouTube platform. If you want your channel meta to be deleted from the dataset, please contact ID R&D Inc. with a topic *\"VoxTube change request\"*.\n\n\nDevelopment\n-----------\n\n\nOfficial repository live repository for opening issues.\n\n\nPlease cite the paper below if you make use of the dataset:\n\n\n''''" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[ "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n", "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[ "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n", "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "region:us" ]

[]

[]

[ "# TL;DR SFT Dataset for OpenAI's Summarize from Feedback task\n\nThe dataset is directly taken from URL\n\nThese columns are taken directly from the aforementioned dataset:\n\n* id: unique identifier for the post\n* subreddit: subreddit the post was taken from\n* title: title of the post\n* post: body of the post\n* summary: summary of the post\n* reference_response: reference response for the post\n\nThese columns are added by this preprocessing script:\n* query: length-limited query for summarization: OAI pre-processes the main text (title + subreddit + post), ensuring it has only 512 tokens; if the main text is too long, then it tries to truncate at the last '\n'. If it's too short it pads the main text (summarize_from_feedback/URL#L98-L165). Padding is either space or '[PAD]' token (see Args below).\n* query_token: tokenized version of 'query'\n* reference_response_token: tokenized version of 'reference_response'\n* reference_response_token_len: length of 'reference_response_token'\n* query_reference_response: concatenation of 'URL()' and 'reference_response'\n* query_reference_response_token: tokenized version of 'query_reference_response', up to 'max_sft_query_response_length' tokens\n* query_reference_response_token_len: length of 'query_reference_response_token'", "# Args" ]

[ "TAGS\n#region-us \n", "# TL;DR SFT Dataset for OpenAI's Summarize from Feedback task\n\nThe dataset is directly taken from URL\n\nThese columns are taken directly from the aforementioned dataset:\n\n* id: unique identifier for the post\n* subreddit: subreddit the post was taken from\n* title: title of the post\n* post: body of the post\n* summary: summary of the post\n* reference_response: reference response for the post\n\nThese columns are added by this preprocessing script:\n* query: length-limited query for summarization: OAI pre-processes the main text (title + subreddit + post), ensuring it has only 512 tokens; if the main text is too long, then it tries to truncate at the last '\n'. If it's too short it pads the main text (summarize_from_feedback/URL#L98-L165). Padding is either space or '[PAD]' token (see Args below).\n* query_token: tokenized version of 'query'\n* reference_response_token: tokenized version of 'reference_response'\n* reference_response_token_len: length of 'reference_response_token'\n* query_reference_response: concatenation of 'URL()' and 'reference_response'\n* query_reference_response_token: tokenized version of 'query_reference_response', up to 'max_sft_query_response_length' tokens\n* query_reference_response_token_len: length of 'query_reference_response_token'", "# Args" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"summarize_from_feedback_oai_preprocessing_1705009345\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"summarize_from_feedback_oai_preprocessing_1705009345\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"EUIPO_QE\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"EUIPO_QE\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.", "## Dataset Details", "### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:", "### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### 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\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Dataset Card Authors [optional]", "## Dataset Card Contact" ]

[ "TAGS\n#region-us \n", "# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.", "## Dataset Details", "### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:", "### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### 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\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Dataset Card Authors [optional]", "## Dataset Card Contact" ]

[ "task_categories:text-generation", "task_ids:language-modeling", "annotations_creators:no-annotation", "language_creators:found", "multilinguality:monolingual", "size_categories:10K<n<100K", "source_datasets:original", "language:es", "license:apache-2.0", "wordslab-webscraper", "region:us" ]

[]

[ "es" ]

[]

[ "TAGS\n#task_categories-text-generation #task_ids-language-modeling #annotations_creators-no-annotation #language_creators-found #multilinguality-monolingual #size_categories-10K<n<100K #source_datasets-original #language-Spanish #license-apache-2.0 #wordslab-webscraper #region-us \n" ]

[ "license:other", "region:us" ]

[]

[]

[ "# Natural Instructions v2 Coreference Tasks\n\n- Project: URL\n- Data source: DataProvenanceInitiative/niv2_submix_original", "## Details\n\nThis dataset contains all coreference examples that were included in the Flan 2022 collection which were orignally published in Super-Natural-Instructions.\n\nThe data is copied from the preprocessed Natural Instructions v2 dataset at DataProvenanceInitiative/niv2_submix_original.\n\nThese tasks are:\n * \"task1391_winogrande_coreference_resolution\"\n * \"task1664_wino_bias_coreference_resolution\"\n * \"task304_numeric_fused_head_coreference_resolution\"\n * \"task892_gap_coreference_resolution\"\n * \"task891_gap_coreference_resolution\"\n * \"task330_gap_coreference_resolution\"\n * \"task401_numeric_fused_head_coreference_resolution\"\n * \"task033_winogrande_coreference_resolution\"\n * \"task133_winowhy_coreference_resolution\"\n * \"task329_gap_coreference_resolution\"\n * \"task249_enhanced_wsc_coreference_resolution\"\n * \"task648_winograd_wsc_coreference_resolution\"\n * \"task1390_wsc_fiexed_coreference_resolution\"\n * \"task893_gap_coreference_resolution\"", "### Fields\n\n- 'inputs': a 'string' feature.\n- 'targets': a 'string' feature.\n- 'task_source': a 'string' feature.\n- 'task_name': a 'string' feature.\n- 'template_type': a 'string' feature." ]

[ "TAGS\n#license-other #region-us \n", "# Natural Instructions v2 Coreference Tasks\n\n- Project: URL\n- Data source: DataProvenanceInitiative/niv2_submix_original", "## Details\n\nThis dataset contains all coreference examples that were included in the Flan 2022 collection which were orignally published in Super-Natural-Instructions.\n\nThe data is copied from the preprocessed Natural Instructions v2 dataset at DataProvenanceInitiative/niv2_submix_original.\n\nThese tasks are:\n * \"task1391_winogrande_coreference_resolution\"\n * \"task1664_wino_bias_coreference_resolution\"\n * \"task304_numeric_fused_head_coreference_resolution\"\n * \"task892_gap_coreference_resolution\"\n * \"task891_gap_coreference_resolution\"\n * \"task330_gap_coreference_resolution\"\n * \"task401_numeric_fused_head_coreference_resolution\"\n * \"task033_winogrande_coreference_resolution\"\n * \"task133_winowhy_coreference_resolution\"\n * \"task329_gap_coreference_resolution\"\n * \"task249_enhanced_wsc_coreference_resolution\"\n * \"task648_winograd_wsc_coreference_resolution\"\n * \"task1390_wsc_fiexed_coreference_resolution\"\n * \"task893_gap_coreference_resolution\"", "### Fields\n\n- 'inputs': a 'string' feature.\n- 'targets': a 'string' feature.\n- 'task_source': a 'string' feature.\n- 'task_name': a 'string' feature.\n- 'template_type': a 'string' feature." ]

[ "task_categories:text-generation", "size_categories:1K<n<10K", "source_datasets:mlabonne/ministack-preferences", "license:odc-by", "region:us" ]

[]

[]

[ "# ministack-preferences-hf_dpo\n\n\nthis is the 'mlabonne/ministack-preferences' dataset simply renamed for ease of use with trl/axolotl\n\n\n\n- also, I took this opportunity to create a nomic topic model with embeddings/etc created on the 'prompt' column, it's fun to play with" ]

[ "TAGS\n#task_categories-text-generation #size_categories-1K<n<10K #source_datasets-mlabonne/ministack-preferences #license-odc-by #region-us \n", "# ministack-preferences-hf_dpo\n\n\nthis is the 'mlabonne/ministack-preferences' dataset simply renamed for ease of use with trl/axolotl\n\n\n\n- also, I took this opportunity to create a nomic topic model with embeddings/etc created on the 'prompt' column, it's fun to play with" ]

[ "license:apache-2.0", "region:us" ]

[]

[]

[ "# Sentiment Analysis (Portuguese) dataset\n\nThis dataset is a concatenation of the 'IMDB 50K', the 'Twitter US Airline Sentiment', App Reviews scraped from Google Play, and the 'EcoPreprocessed'.\n\n- Note: Samples were translated via the Google Translate API." ]

[ "TAGS\n#license-apache-2.0 #region-us \n", "# Sentiment Analysis (Portuguese) dataset\n\nThis dataset is a concatenation of the 'IMDB 50K', the 'Twitter US Airline Sentiment', App Reviews scraped from Google Play, and the 'EcoPreprocessed'.\n\n- Note: Samples were translated via the Google Translate API." ]

[ "task_categories:text-generation", "size_categories:100K<n<1M", "language:en", "license:other", "casual", "internet-culture", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#task_categories-text-generation #size_categories-100K<n<1M #language-English #license-other #casual #internet-culture #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of cloudyu/Mixtral_7Bx6_MoE_35B\n\n\n\nDataset automatically created during the evaluation run of model cloudyu/Mixtral_7Bx6_MoE_35B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-14T16:00:09.048254(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## Dataset Details", "### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:", "### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### 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\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Dataset Card Authors [optional]", "## Dataset Card Contact" ]

[ "TAGS\n#region-us \n", "# Dataset Card for Evaluation run of cloudyu/Mixtral_7Bx6_MoE_35B\n\n\n\nDataset automatically created during the evaluation run of model cloudyu/Mixtral_7Bx6_MoE_35B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-14T16:00:09.048254(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## Dataset Details", "### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:", "### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### 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\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Dataset Card Authors [optional]", "## Dataset Card Contact" ]

[ "task_categories:text-retrieval", "task_ids:document-retrieval", "multilinguality:monolingual", "size_categories:1K<n<10K", "source_datasets:Ko-StrategyQA", "language:ko", "text-retrieval", "region:us" ]

[]

[ "ko" ]

[ "# Ko-StrategyQA\n\nThis dataset represents a conversion of the Ko-StrategyQA dataset into the BeIR format, making it compatible for use with mteb.\n\nThe original dataset was designed for multi-hop QA, so we processed the data accordingly. First, we grouped the evidence documents tagged by annotators into sets, and excluded unit questions containing 'no_evidence' or 'operation'." ]

[ "TAGS\n#task_categories-text-retrieval #task_ids-document-retrieval #multilinguality-monolingual #size_categories-1K<n<10K #source_datasets-Ko-StrategyQA #language-Korean #text-retrieval #region-us \n", "# Ko-StrategyQA\n\nThis dataset represents a conversion of the Ko-StrategyQA dataset into the BeIR format, making it compatible for use with mteb.\n\nThe original dataset was designed for multi-hop QA, so we processed the data accordingly. First, we grouped the evidence documents tagged by annotators into sets, and excluded unit questions containing 'no_evidence' or 'operation'." ]

[ "task_categories:image-to-text", "size_categories:10K<n<100K", "language:en", "license:unknown", "code", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#task_categories-image-to-text #size_categories-10K<n<100K #language-English #license-unknown #code #region-us \n" ]

[ "task_categories:object-detection", "size_categories:10K<n<100K", "license:apache-2.0", "show_bussiness", "region:us" ]

[]

[]

[ "# StageVision V1 OD > 2024-01-15 12:07am\nURL\n\nProvided by a Roboflow user\nLicense: CC BY 4.0\n\nStageVision V1 OD - v1 2024-01-15 12:07am\n==============================\n\nThis dataset was exported via URL on January 14, 2024 at 11:10 PM GMT\n\nRoboflow is an end-to-end computer vision platform that helps you\n* collaborate with your team on computer vision projects\n* collect & organize images\n* understand and search unstructured image data\n* annotate, and create datasets\n* export, train, and deploy computer vision models\n* use active learning to improve your dataset over time\n\nFor state of the art Computer Vision training notebooks you can use with this dataset,\nvisit URL\n\nTo find over 100k other datasets and pre-trained models, visit URL\n\nThe dataset includes 24000 images.\nStage_Items are annotated in YOLOv8 format.\n\nThe following pre-processing was applied to each image:\n* Auto-orientation of pixel data (with EXIF-orientation stripping)\n* Resize to 640x640 (Stretch)\n\nThe following augmentation was applied to create 3 versions of each source image:\n* Random Gaussian blur of between 0 and 1.4 pixels\n* Salt and pepper noise was applied to 1.96 percent of pixels" ]

[ "TAGS\n#task_categories-object-detection #size_categories-10K<n<100K #license-apache-2.0 #show_bussiness #region-us \n", "# StageVision V1 OD > 2024-01-15 12:07am\nURL\n\nProvided by a Roboflow user\nLicense: CC BY 4.0\n\nStageVision V1 OD - v1 2024-01-15 12:07am\n==============================\n\nThis dataset was exported via URL on January 14, 2024 at 11:10 PM GMT\n\nRoboflow is an end-to-end computer vision platform that helps you\n* collaborate with your team on computer vision projects\n* collect & organize images\n* understand and search unstructured image data\n* annotate, and create datasets\n* export, train, and deploy computer vision models\n* use active learning to improve your dataset over time\n\nFor state of the art Computer Vision training notebooks you can use with this dataset,\nvisit URL\n\nTo find over 100k other datasets and pre-trained models, visit URL\n\nThe dataset includes 24000 images.\nStage_Items are annotated in YOLOv8 format.\n\nThe following pre-processing was applied to each image:\n* Auto-orientation of pixel data (with EXIF-orientation stripping)\n* Resize to 640x640 (Stretch)\n\nThe following augmentation was applied to create 3 versions of each source image:\n* Random Gaussian blur of between 0 and 1.4 pixels\n* Salt and pepper noise was applied to 1.96 percent of pixels" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"en-test\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"en-test\"\n\nMore Information needed" ]

[ "language:ms", "license:mit", "region:us" ]

[]

[ "ms" ]

[ "# Mixtral Malaysian RAG\n\nSimulate Multi-turn RAG conversations, some questions purposely asked out-of-context and the users throw random rubbish replies.\n\nnotebooks at URL\n\n- URL, 327980 rows, 4.1 GB\n- URL, 169403 rows, 2.45 GB\n- URL, 339627 rows, 3.08 GB", "## Example data" ]

[ "TAGS\n#language-Malay (macrolanguage) #license-mit #region-us \n", "# Mixtral Malaysian RAG\n\nSimulate Multi-turn RAG conversations, some questions purposely asked out-of-context and the users throw random rubbish replies.\n\nnotebooks at URL\n\n- URL, 327980 rows, 4.1 GB\n- URL, 169403 rows, 2.45 GB\n- URL, 339627 rows, 3.08 GB", "## Example data" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[ "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n", "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[ "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n", "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[ "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n", "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[ "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n", "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[ "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n", "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[ "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n", "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[ "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n", "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[ "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n", "### Load Raw Dataset with Waifuc\n\n\nWe provide raw dataset (including tagged images) for waifuc loading. If you need this, just run the following code\n\n\nList of Clusters\n----------------\n\n\nList of tag clustering result, maybe some outfits can be mined here.", "### Raw Text Version", "### Table Version" ]

[ "task_categories:conversational", "size_categories:10K<n<100K", "language:ja", "license:llama2", "region:us" ]

[]

[ "ja" ]

[ "# Model\nURL", "# Dataset\nURL", "# Compute by\nTsuginosuke AI SuperComputer\nFreeAI Ltd.\n\nURL" ]

[ "TAGS\n#task_categories-conversational #size_categories-10K<n<100K #language-Japanese #license-llama2 #region-us \n", "# Model\nURL", "# Dataset\nURL", "# Compute by\nTsuginosuke AI SuperComputer\nFreeAI Ltd.\n\nURL" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"distilabel_dpo_pairs_binarized\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"distilabel_dpo_pairs_binarized\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"20240108_chai_prize_reward_model_data\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"20240108_chai_prize_reward_model_data\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"myriade_noun_aligned_with_wordnet_noun_sens\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"myriade_noun_aligned_with_wordnet_noun_sens\"\n\nMore Information needed" ]

[ "task_categories:question-answering", "size_categories:10K<n<100K", "language:en", "license:mit", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#task_categories-question-answering #size_categories-10K<n<100K #language-English #license-mit #region-us \n" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "language:zh", "region:us" ]

[]

[ "zh" ]

[]

[ "TAGS\n#language-Chinese #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# 此文件夹用于放置训练3D-LLM的数据", "## URL\n收集所有的scannet数据集并将其用jsong文件保存，数据格式如下", "## scannet_w_id.json\n收集所有的scannet数据集并将其用jsong文件保存，数据格式为数字标签，未映射" ]

[ "TAGS\n#region-us \n", "# 此文件夹用于放置训练3D-LLM的数据", "## URL\n收集所有的scannet数据集并将其用jsong文件保存，数据格式如下", "## scannet_w_id.json\n收集所有的scannet数据集并将其用jsong文件保存，数据格式为数字标签，未映射" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"vsums_synthetic_gpt4_deduped_small\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"vsums_synthetic_gpt4_deduped_small\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"EUIPO_AE\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"EUIPO_AE\"\n\nMore Information needed" ]

[ "task_categories:fill-mask", "task_ids:masked-language-modeling", "size_categories:1M<n<10M", "language:en", "license:cc-by-4.0", "business", "company website", "industry classification", "region:us" ]

[]

[ "en" ]

[ "# Dataset Card for \"CompanyWeb\"", "### Dataset Summary\n\nThe dataset contains textual content extracted from 1,788,413 company web pages of 393,542 companies. The companies included in the dataset are small, medium and large international enterprises including publicly listed companies. Additional company information is provided in form of the corresponding Standard Industry Classification (SIC) label 'sic4'. \nThe text includes all textual information contained on the website with a timeline ranging from 2014 to 2021. The search includes all subsequent pages with links from the homepage containing the company domain name. \nWe filter the resulting textual data to only include English text utilizing the FastText language detection API (Joulin et al., 2016).", "### Languages\n\n- en", "## Dataset Structure", "### Data Instances\n\n- #Instances: 1789413\n- #Companies: 393542\n- #Timeline: 2014-2021", "### Data Fields\n\n- 'id': instance identifier '(string)'\n- 'cid': company identifier '(string)'\n- 'text': website text '(string)'\n- 'sic4': 4-digit SIC '(string)'" ]

[ "TAGS\n#task_categories-fill-mask #task_ids-masked-language-modeling #size_categories-1M<n<10M #language-English #license-cc-by-4.0 #business #company website #industry classification #region-us \n", "# Dataset Card for \"CompanyWeb\"", "### Dataset Summary\n\nThe dataset contains textual content extracted from 1,788,413 company web pages of 393,542 companies. The companies included in the dataset are small, medium and large international enterprises including publicly listed companies. Additional company information is provided in form of the corresponding Standard Industry Classification (SIC) label 'sic4'. \nThe text includes all textual information contained on the website with a timeline ranging from 2014 to 2021. The search includes all subsequent pages with links from the homepage containing the company domain name. \nWe filter the resulting textual data to only include English text utilizing the FastText language detection API (Joulin et al., 2016).", "### Languages\n\n- en", "## Dataset Structure", "### Data Instances\n\n- #Instances: 1789413\n- #Companies: 393542\n- #Timeline: 2014-2021", "### Data Fields\n\n- 'id': instance identifier '(string)'\n- 'cid': company identifier '(string)'\n- 'text': website text '(string)'\n- 'sic4': 4-digit SIC '(string)'" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"kmdb_people_classification\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"kmdb_people_classification\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"kmdb_institution_classification\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"kmdb_institution_classification\"\n\nMore Information needed" ]

[ "task_categories:text-classification", "language:da", "license:mit", "chemistry", "biology", "finance", "legal", "music", "art", "webdataset", "arxiv:2209.11055", "region:us" ]

[ "2209.11055" ]

[ "da" ]

[ "# Danish Wikipedia Categories\n\nThe dataset was created entirely from the last Danish Wikipedia dump\nby traversing the category hierarchy in the categorylinks table.\n\nAll categories that were one level bellow the topcategories, and which had more than 30 articles assigned to them were selected.\nIn order to see whether an article belongs to a certain category I checked, whether the article was connected to the category in the directed graph of the category hierarchy.\nIf the length of the path between the article and a category was less than or equal to 5 edges (arbitrary choice, but I found it to work well),\nthe category was assigned to the article.\n\nNote that this is a multilabel classification task.\nIts purpose is to train sentence transformers for the DFM project using a technique similar to SetFit." ]

[ "TAGS\n#task_categories-text-classification #language-Danish #license-mit #chemistry #biology #finance #legal #music #art #webdataset #arxiv-2209.11055 #region-us \n", "# Danish Wikipedia Categories\n\nThe dataset was created entirely from the last Danish Wikipedia dump\nby traversing the category hierarchy in the categorylinks table.\n\nAll categories that were one level bellow the topcategories, and which had more than 30 articles assigned to them were selected.\nIn order to see whether an article belongs to a certain category I checked, whether the article was connected to the category in the directed graph of the category hierarchy.\nIf the length of the path between the article and a category was less than or equal to 5 edges (arbitrary choice, but I found it to work well),\nthe category was assigned to the article.\n\nNote that this is a multilabel classification task.\nIts purpose is to train sentence transformers for the DFM project using a technique similar to SetFit." ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"rna_blue_1024\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"rna_blue_1024\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"rna_green_1024\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"rna_green_1024\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"audioset_extract_unit\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"audioset_extract_unit\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"kmdb_relation_extraction\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"kmdb_relation_extraction\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"endless-sky-master\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"endless-sky-master\"\n\nMore Information needed" ]

[ "task_categories:image-to-text", "language:la", "language:fr", "license:mit", "region:us" ]

[]

[ "la", "fr" ]

[ "# Himanis Dataset", "## Table of Contents\n- Himanis Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: Himanis\n- Paper: Paper\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nHimanis (Historical MAnuscript Indexing for user controlled Search) is a corpus of medieval documents.", "### Languages\n\nAll the documents in the dataset are written in Latin and in French.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "TAGS\n#task_categories-image-to-text #language-Latin #language-French #license-mit #region-us \n", "# Himanis Dataset", "## Table of Contents\n- Himanis Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: Himanis\n- Paper: Paper\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nHimanis (Historical MAnuscript Indexing for user controlled Search) is a corpus of medieval documents.", "### Languages\n\nAll the documents in the dataset are written in Latin and in French.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "task_categories:image-to-text", "language:la", "license:mit", "region:us" ]

[]

[ "la" ]

[ "# HOME Alcar Dataset", "## Table of Contents\n- Alcar Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: HOME\n- Source: Arkindex\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nThe HOME-Alcar (Aligned and Annotated Cartularies) dataset is a Medieval corpus. The 17 medieval manuscripts in this corpus are cartularies, i.e. books copying charters and legal acts, produced between the 12th and 14th centuries.", "### Languages\n\nAll the documents in the dataset are written in Latin.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "TAGS\n#task_categories-image-to-text #language-Latin #license-mit #region-us \n", "# HOME Alcar Dataset", "## Table of Contents\n- Alcar Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: HOME\n- Source: Arkindex\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nThe HOME-Alcar (Aligned and Annotated Cartularies) dataset is a Medieval corpus. The 17 medieval manuscripts in this corpus are cartularies, i.e. books copying charters and legal acts, produced between the 12th and 14th centuries.", "### Languages\n\nAll the documents in the dataset are written in Latin.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "task_categories:image-to-text", "language:de", "license:mit", "region:us" ]

[]

[ "de" ]

[ "# NewsEye Dataset", "## Table of Contents\n- NewsEye Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: NewsEye project\n- Source: Zenodo\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nThe dataset comprises Austrian newspaper pages from 19th and early 20th century. The images were provided by the Austrian National Library.", "### Languages\n\nThe documents are in Austrian German with the Fraktur font.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "TAGS\n#task_categories-image-to-text #language-German #license-mit #region-us \n", "# NewsEye Dataset", "## Table of Contents\n- NewsEye Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: NewsEye project\n- Source: Zenodo\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nThe dataset comprises Austrian newspaper pages from 19th and early 20th century. The images were provided by the Austrian National Library.", "### Languages\n\nThe documents are in Austrian German with the Fraktur font.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "task_categories:image-to-text", "language:nb", "license:mit", "region:us" ]

[]

[ "nb" ]

[ "# NorHand v1 Dataset", "## Table of Contents\n- NorHand v1 Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: Hugin-Munin project\n- Source: Zenodo\n- Paper: A Comprehensive Comparison of Open-Source Libraries for Handwritten Text Recognition in Norwegian\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nThe NorHand v1 dataset comprises Norwegian letter and diary line images and text from 19th and early 20th century.", "### Languages\n\nAll the documents in the dataset are written in Norwegian Bokmål.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "TAGS\n#task_categories-image-to-text #language-Norwegian Bokmål #license-mit #region-us \n", "# NorHand v1 Dataset", "## Table of Contents\n- NorHand v1 Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: Hugin-Munin project\n- Source: Zenodo\n- Paper: A Comprehensive Comparison of Open-Source Libraries for Handwritten Text Recognition in Norwegian\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nThe NorHand v1 dataset comprises Norwegian letter and diary line images and text from 19th and early 20th century.", "### Languages\n\nAll the documents in the dataset are written in Norwegian Bokmål.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "task_categories:image-to-text", "language:nb", "license:mit", "region:us" ]

[]

[ "nb" ]

[ "# NorHand v2 Dataset", "## Table of Contents\n- NorHand v2 Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: Hugin-Munin project\n- Source: Zenodo\n- Point of Contact: TEKLIA", "## Dataset Summary\n\nThe NorHand v2 dataset comprises Norwegian letter and diary line images and text from 19th and early 20th century.", "### Languages\n\nAll the documents in the dataset are written in Norwegian Bokmål.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "TAGS\n#task_categories-image-to-text #language-Norwegian Bokmål #license-mit #region-us \n", "# NorHand v2 Dataset", "## Table of Contents\n- NorHand v2 Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: Hugin-Munin project\n- Source: Zenodo\n- Point of Contact: TEKLIA", "## Dataset Summary\n\nThe NorHand v2 dataset comprises Norwegian letter and diary line images and text from 19th and early 20th century.", "### Languages\n\nAll the documents in the dataset are written in Norwegian Bokmål.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "task_categories:image-to-text", "language:nb", "license:mit", "region:us" ]

[]

[ "nb" ]

[ "# NorHand v3 Dataset", "## Table of Contents\n- NorHand v3 Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: Hugin-Munin project\n- Source: Zenodo\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nThe NorHand v3 dataset comprises Norwegian letter and diary line images and text from 19th and early 20th century.", "### Languages\n\nAll the documents in the dataset are written in Norwegian Bokmål.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "TAGS\n#task_categories-image-to-text #language-Norwegian Bokmål #license-mit #region-us \n", "# NorHand v3 Dataset", "## Table of Contents\n- NorHand v3 Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: Hugin-Munin project\n- Source: Zenodo\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nThe NorHand v3 dataset comprises Norwegian letter and diary line images and text from 19th and early 20th century.", "### Languages\n\nAll the documents in the dataset are written in Norwegian Bokmål.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "task_categories:image-to-text", "language:fr", "license:mit", "region:us" ]

[]

[ "fr" ]

[ "# Belfort Dataset", "## Table of Contents\n- Belfort Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: Belfort city archives\n- Source: Zenodo\n- Paper: Handwritten Text Recognition from Crowdsourced Annotations\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nThe Belfort dataset includes minutes of the municipal council of the French city of Belfort. \nText lines were extracted using an automatic model and may contain segmentation errors. The transcriptions were obtained through a crowdsourcing campaign using the Callico web plateform.", "### Languages\n\nAll the documents in the dataset are written in French.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "TAGS\n#task_categories-image-to-text #language-French #license-mit #region-us \n", "# Belfort Dataset", "## Table of Contents\n- Belfort Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: Belfort city archives\n- Source: Zenodo\n- Paper: Handwritten Text Recognition from Crowdsourced Annotations\n- Point of Contact: TEKLIA", "## Dataset Summary \n\nThe Belfort dataset includes minutes of the municipal council of the French city of Belfort. \nText lines were extracted using an automatic model and may contain segmentation errors. The transcriptions were obtained through a crowdsourcing campaign using the Callico web plateform.", "### Languages\n\nAll the documents in the dataset are written in French.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "task_categories:image-to-text", "language:en", "license:mit", "region:us" ]

[]

[ "en" ]

[ "# IAM Dataset", "## Table of Contents\n- IAM Dataset\n - Table of Contents\n - Dataset Description\n - Dataset Summary\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: IAM Handwriting Database\n- Paper: The IAM-database: an English sentence database for offline handwriting recognition\n- Point of Contact: TEKLIA", "## Dataset Summary\n\nThe IAM Handwriting Database contains forms of handwritten English text which can be used to train and test handwritten text recognizers and to perform writer identification and verification experiments.", "### Languages\n\nAll the documents in the dataset are written in English.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "TAGS\n#task_categories-image-to-text #language-English #license-mit #region-us \n", "# IAM Dataset", "## Table of Contents\n- IAM Dataset\n - Table of Contents\n - Dataset Description\n - Dataset Summary\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: IAM Handwriting Database\n- Paper: The IAM-database: an English sentence database for offline handwriting recognition\n- Point of Contact: TEKLIA", "## Dataset Summary\n\nThe IAM Handwriting Database contains forms of handwritten English text which can be used to train and test handwritten text recognizers and to perform writer identification and verification experiments.", "### Languages\n\nAll the documents in the dataset are written in English.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "task_categories:image-to-text", "language:zh", "license:mit", "region:us" ]

[]

[ "zh" ]

[ "# CASIA Dataset", "## Table of Contents\n- CASIA Dataset\n - Table of Contents\n - Dataset Description\n - Dataset Summary\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: CASIA\n- Paper: Online and offline handwritten Chinese character recognition: Benchmarking on new databases\n- Point of Contact: TEKLIA", "## Dataset Summary\n\nThe offline Chinese handwriting database (CASIA-HWDB) was built by the National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences (CASIA). \nThe handwritten samples were produced by 1,020 writers using Anoto pen on papers, such that both online and offline data were obtained.", "### Languages\n\nAll the documents in the dataset are written in Chinese.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "TAGS\n#task_categories-image-to-text #language-Chinese #license-mit #region-us \n", "# CASIA Dataset", "## Table of Contents\n- CASIA Dataset\n - Table of Contents\n - Dataset Description\n - Dataset Summary\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: CASIA\n- Paper: Online and offline handwritten Chinese character recognition: Benchmarking on new databases\n- Point of Contact: TEKLIA", "## Dataset Summary\n\nThe offline Chinese handwriting database (CASIA-HWDB) was built by the National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences (CASIA). \nThe handwritten samples were produced by 1,020 writers using Anoto pen on papers, such that both online and offline data were obtained.", "### Languages\n\nAll the documents in the dataset are written in Chinese.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "task_categories:image-to-text", "language:fr", "license:mit", "region:us" ]

[]

[ "fr" ]

[ "# POPP Dataset", "## Table of Contents\n- POPP Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: POPP\n- Source: GitHub\n- Paper: Recognition and Information Extraction in Historical Handwritten Tables: Toward Understanding Early 20th Century Paris Census\n- Point of Contact: TEKLIA", "## Dataset Summary\n\nThe POPP dataset includes French civil census from Paris from the early 20th century.", "### Languages\n\nAll the documents in the dataset are written in French.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "TAGS\n#task_categories-image-to-text #language-French #license-mit #region-us \n", "# POPP Dataset", "## Table of Contents\n- POPP Dataset\n - Table of Contents\n - Dataset Description\n - Languages\n - Dataset Structure\n - Data Instances\n - Data Fields", "## Dataset Description\n\n- Homepage: POPP\n- Source: GitHub\n- Paper: Recognition and Information Extraction in Historical Handwritten Tables: Toward Understanding Early 20th Century Paris Census\n- Point of Contact: TEKLIA", "## Dataset Summary\n\nThe POPP dataset includes French civil census from Paris from the early 20th century.", "### Languages\n\nAll the documents in the dataset are written in French.", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n\n- 'image': A PIL.Image.Image object containing the image. Note that when accessing the image column: dataset[0][\"image\"] the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the \"image\" column, i.e. dataset[0][\"image\"] should always be preferred over dataset[\"image\"][0].\n- 'text': the label transcription of the image." ]

[ "region:us" ]

[]

[]

[ "# Medmcqa mixtral openchat 0.1\n\nThis dataset is a small subset of Medmcqa where asked mixtral / openchat3.5 models to answer medical questions and give some explanations.\nTo ensure the results are correct, we gave some useful information in the prompt to help the model to answer correct. We discarded those useful information from the question we put in this dataset.\nBy doing this, we can have a structured and accurate answer built by the LLM.\n\nThis dataset can be used to finetuned LLMs on medical question answering.\n\nCurrently, the dataset is really small, this is the version 0.1. In the next versions, we will try to build a bigger version and to include other languages." ]

[ "TAGS\n#region-us \n", "# Medmcqa mixtral openchat 0.1\n\nThis dataset is a small subset of Medmcqa where asked mixtral / openchat3.5 models to answer medical questions and give some explanations.\nTo ensure the results are correct, we gave some useful information in the prompt to help the model to answer correct. We discarded those useful information from the question we put in this dataset.\nBy doing this, we can have a structured and accurate answer built by the LLM.\n\nThis dataset can be used to finetuned LLMs on medical question answering.\n\nCurrently, the dataset is really small, this is the version 0.1. In the next versions, we will try to build a bigger version and to include other languages." ]

[ "region:us" ]

[]

[]

[ "# Works\n- ./subdir/URL # Works\n- ./subdir # Does not work" ]

[ "TAGS\n#region-us \n", "# Works\n- ./subdir/URL # Works\n- ./subdir # Does not work" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"dpoOlier\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"dpoOlier\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"fashion_image_caption_100-v2\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"fashion_image_caption_100-v2\"\n\nMore Information needed" ]

[ "task_categories:depth-estimation", "size_categories:1K<n<10K", "license:mit", "lidar", "satellite", "image", "region:us" ]

[]

[]

[ "# 2020 Santa Clara LiDaR and Satellite Image Dataset", "## Overview\n\nThis dataset is collection of LiDaR and Satellite images of Santa Clara, California. This dataset is specifically designed for advanced depth estimation using 2D satellite images. The dataset is collected from NOAA and Google Earth.", "## Dataset", "### Total Dataset Size\n\n- Number of Objects: 6,046\n- Size on Disk: 733.1 GB", "### Specified Objects in the Dataset\n\n1. Edited2020SantaClaraLiDarDataset.geojson\n - Type: GeoJSON\n - Size: 895.2 KB\n - Total Objects: 1\n\n2. images_v2/ (Folder)\n - Comment: RAW Satellite Images\n - Total Size: 588.0 GB\n - Number of Objects: 2015\n\n3. images/ (Folder)\n - Comment: Compressed Satellite Images\n - Total Size: 5.3 GB\n - Number of Objects: 2015\n\n4. LAZ/ (Folder)\n - Comment: LiDaR LAZ Files\n - Total Size: 139.7 GB\n - Number of Objects: 2015", "### Additional Information", "#### Creators;\n\n- Umut YILDIRIM\n- Shreyas Joshi", "#### License:\n\nMIT License \n\n_Note: The dataset is particularly useful for deep learning applications in lidar data processing and analysis, offering a rich source of geospatial data._\n\n_Note: This repo is under MIT License. However, if you intend to use the Google Earth imagery for commercial purposes, you will need to obtain permission through this Google form._" ]

[ "TAGS\n#task_categories-depth-estimation #size_categories-1K<n<10K #license-mit #lidar #satellite #image #region-us \n", "# 2020 Santa Clara LiDaR and Satellite Image Dataset", "## Overview\n\nThis dataset is collection of LiDaR and Satellite images of Santa Clara, California. This dataset is specifically designed for advanced depth estimation using 2D satellite images. The dataset is collected from NOAA and Google Earth.", "## Dataset", "### Total Dataset Size\n\n- Number of Objects: 6,046\n- Size on Disk: 733.1 GB", "### Specified Objects in the Dataset\n\n1. Edited2020SantaClaraLiDarDataset.geojson\n - Type: GeoJSON\n - Size: 895.2 KB\n - Total Objects: 1\n\n2. images_v2/ (Folder)\n - Comment: RAW Satellite Images\n - Total Size: 588.0 GB\n - Number of Objects: 2015\n\n3. images/ (Folder)\n - Comment: Compressed Satellite Images\n - Total Size: 5.3 GB\n - Number of Objects: 2015\n\n4. LAZ/ (Folder)\n - Comment: LiDaR LAZ Files\n - Total Size: 139.7 GB\n - Number of Objects: 2015", "### Additional Information", "#### Creators;\n\n- Umut YILDIRIM\n- Shreyas Joshi", "#### License:\n\nMIT License \n\n_Note: The dataset is particularly useful for deep learning applications in lidar data processing and analysis, offering a rich source of geospatial data._\n\n_Note: This repo is under MIT License. However, if you intend to use the Google Earth imagery for commercial purposes, you will need to obtain permission through this Google form._" ]

[ "task_categories:translation", "task_categories:audio-to-audio", "task_categories:automatic-speech-recognition", "annotations_creators:found", "annotations_creators:expert-generated", "annotations_creators:machine-generated", "language_creators:crowdsourced", "multilinguality:translation", "size_categories:10K<n<100K", "source_datasets:original", "language:es", "language:ca", "language:gl", "language:eu", "license:cc0-1.0", "region:us" ]

[]

[ "es", "ca", "gl", "eu" ]

[ "# Dataset Card for escagleu-64K corpus", "## Table of Contents\n- Dataset Description\n - Dataset Summary\n - Supported Tasks\n - Languages\n- Dataset Structure\n - Data Splits\n- Dataset Creation\n - Source Data\n - Personal and Sensitive Information\n- Considerations for Using the Data\n - Social Impact of Dataset\n - Discussion of Biases\n - Other Known Limitations\n- Additional Information\n - Author\n - Contact Information\n - Copyright\n - Licensing information\n - Funding", "## Dataset Description", "### Dataset Summary\n\nescagleu-64k is a parallel corpus comprising 64184 sentences translated among Spanish, Catalan, Valencian Catalan, Galician, and Basque.\n\nThe original sentences are in Spanish and come from the Spanish Common Voice Corpus.\n\nWe prepared this corpus with the aim of creating a parallel speech dataset among these languages using the Common Voice platform between the frame of the project Ilenia.\n\n*Warning: The translation into Galician and Basque was done through machine translation, and post-editing is required. Additionally, we have identified some errors in the source sentences. A subsequent version of the corpus will include reviewed translations and source sentences.*\n\nThis work is licensed under a CC0 International License.", "### Supported Tasks and Leaderboards\n\nThis dataset can be used for training Machine Translation (MT) models, Speech-to-Text translation models, and Speech-to-Speech translation models.", "### Languages\n\nThis multilingual dataset is in Spanish (es), Catalan (ca), Valencian Catalan (ca-va), Galician (gl) and Basque (eu).", "## Dataset Structure\nFive separated tsv files are provided with the sentences sorted in the same order:\n\n* escagleu-64k_ca.tsv: contains 64184 sentences translated into Catalan.\n* escagleu-64k_ca_va.tsv: contains 64184 sentences adapted into Valencian Catalan.\n* escagleu-64k_es.tsv: contains 64184 sentences in Spanish (authentic).\n* escagleu-64k_gl.tsv: contains 64184 sentences translated into Galician using MT. \n* escagleu-64k_es.tsv: contains 64184 sentences translated into Basque using MT.\n \nIn addition, a tsv is provided with the sentences aligned in all the languages:\n\n* URL: the sentences in all the languages of the corpus.", "### Data Splits\n\nThe dataset contains a single split.", "## Dataset Creation", "### Curation Rationale\n\nWe created this corpus with the goal of establishing a parallel speech dataset among Spanish, Catalan, Galician, and Basque using the Common Voice platform. The resulting dataset will be employed to train Speech-to-Text and Speech-to-Speech translation models.", "### Source Data\n\nThe original sentences are in Spanish and come from the Spanish Common Voice Corpus.", "#### Initial Data Collection and Normalization\n\nWe extracted a set of 223,261 sentences from the Spanish Common Voice Corpus v.07.\n\nAn automatic selection was performed, removing sentences that:\n\n* Were repeated.\n* Exceeded 14 words in length.\n* Ended with a preposition.\n* Were in lowercase but Out of Vocabulary (OOV), utilizing the Hunspell dictionary.\n* Contained repeated words.\n* Featured characters not existing in Spanish or sequences of characters impossible in Spanish.\n\nThis filtering process resulted in the current selection of sentences. For some of these sentences, we conducted manual or automatic adjustments, such as capitalization, punctuation fixes, etc.\n\nThe selected sentences were translated from Spanish into Catalan by a professional translation company. Subsequently, they were adapted into Valencian by an expert team from the Universitat d'Alacant.\n\nThe same corpus of sentences was translated into Galician using NOS-MT-OpenNMT-es-gl and into Basque using itzuli.\n\nA subsequent version of the corpus will include reviewed translations and source sentences.", "#### Who are the source language producers?\n\nThe Common Voice is a corpus designed for speech-related tasks. The recorded sentences are sourced from diverse origins. For more information, please refer to the project repository.", "### Annotations\n\nThis corpus doesn't have annotations.", "#### Annotation process\n\nN/A", "#### Who are the annotators?\n\nN/A", "### Personal and Sensitive Information\n\nThe original sentences are in Spanish and come from the Spanish Common Voice Corpus. To our knowledge, there are no private person’s personal identifiers or sensitive information.", "## Considerations for Using the Data", "### Social Impact of Dataset\n\nWe expect that this corpus will contribute to the development of speech technologies in the targeted languages.", "### Discussion of Biases\n\nWe are aware that some of the sentences in the corpus may convey stereotypes. Nonetheless, we have not applied any steps to reduce their impact.", "### Other Known Limitations\n\nThe translation into Galician and Basque was done through machine translation, and post-editing is required. Additionally, we have identified some errors in the source sentences. A subsequent version of the corpus will include reviewed translations and source sentences.", "## Additional Information", "### Authors\nGrupo de Procesamiento del Lenguaje Natural y Sistemas de Información, Centro de Inteligencia Digital (CENID, Universidad de Alicante),\n\nHizkuntza eta Politika Saila (Eusko Jaurlaritza),\n\nHiTZ Center - Aholab, University of the Basque Country UPV/EHU, \n\nLanguage Technologies Unit (LangTech) at the Barcelona Supercomputing Center (BSC),\n\nProxecto Nós (Universidade de Santiago de Compostela).", "### Contact information\nFor further information, please send an email to langtech@URL.", "### Copyright\nCopyright Language Technologies Unit at Barcelona Supercomputing Center (2023).", "### Licensing information\nThis work is licensed under a CC.", "### Funding\n\nThis work is funded by the Ministerio de Asuntos Económicos y Transformación Digital and Plan de Recuperación, Transformación y Resiliencia - Funded by EU – NextGenerationEU within the framework of the project ILENIA with reference 2022/TL22/00215337." ]

[ "TAGS\n#task_categories-translation #task_categories-audio-to-audio #task_categories-automatic-speech-recognition #annotations_creators-found #annotations_creators-expert-generated #annotations_creators-machine-generated #language_creators-crowdsourced #multilinguality-translation #size_categories-10K<n<100K #source_datasets-original #language-Spanish #language-Catalan #language-Galician #language-Basque #license-cc0-1.0 #region-us \n", "# Dataset Card for escagleu-64K corpus", "## Table of Contents\n- Dataset Description\n - Dataset Summary\n - Supported Tasks\n - Languages\n- Dataset Structure\n - Data Splits\n- Dataset Creation\n - Source Data\n - Personal and Sensitive Information\n- Considerations for Using the Data\n - Social Impact of Dataset\n - Discussion of Biases\n - Other Known Limitations\n- Additional Information\n - Author\n - Contact Information\n - Copyright\n - Licensing information\n - Funding", "## Dataset Description", "### Dataset Summary\n\nescagleu-64k is a parallel corpus comprising 64184 sentences translated among Spanish, Catalan, Valencian Catalan, Galician, and Basque.\n\nThe original sentences are in Spanish and come from the Spanish Common Voice Corpus.\n\nWe prepared this corpus with the aim of creating a parallel speech dataset among these languages using the Common Voice platform between the frame of the project Ilenia.\n\n*Warning: The translation into Galician and Basque was done through machine translation, and post-editing is required. Additionally, we have identified some errors in the source sentences. A subsequent version of the corpus will include reviewed translations and source sentences.*\n\nThis work is licensed under a CC0 International License.", "### Supported Tasks and Leaderboards\n\nThis dataset can be used for training Machine Translation (MT) models, Speech-to-Text translation models, and Speech-to-Speech translation models.", "### Languages\n\nThis multilingual dataset is in Spanish (es), Catalan (ca), Valencian Catalan (ca-va), Galician (gl) and Basque (eu).", "## Dataset Structure\nFive separated tsv files are provided with the sentences sorted in the same order:\n\n* escagleu-64k_ca.tsv: contains 64184 sentences translated into Catalan.\n* escagleu-64k_ca_va.tsv: contains 64184 sentences adapted into Valencian Catalan.\n* escagleu-64k_es.tsv: contains 64184 sentences in Spanish (authentic).\n* escagleu-64k_gl.tsv: contains 64184 sentences translated into Galician using MT. \n* escagleu-64k_es.tsv: contains 64184 sentences translated into Basque using MT.\n \nIn addition, a tsv is provided with the sentences aligned in all the languages:\n\n* URL: the sentences in all the languages of the corpus.", "### Data Splits\n\nThe dataset contains a single split.", "## Dataset Creation", "### Curation Rationale\n\nWe created this corpus with the goal of establishing a parallel speech dataset among Spanish, Catalan, Galician, and Basque using the Common Voice platform. The resulting dataset will be employed to train Speech-to-Text and Speech-to-Speech translation models.", "### Source Data\n\nThe original sentences are in Spanish and come from the Spanish Common Voice Corpus.", "#### Initial Data Collection and Normalization\n\nWe extracted a set of 223,261 sentences from the Spanish Common Voice Corpus v.07.\n\nAn automatic selection was performed, removing sentences that:\n\n* Were repeated.\n* Exceeded 14 words in length.\n* Ended with a preposition.\n* Were in lowercase but Out of Vocabulary (OOV), utilizing the Hunspell dictionary.\n* Contained repeated words.\n* Featured characters not existing in Spanish or sequences of characters impossible in Spanish.\n\nThis filtering process resulted in the current selection of sentences. For some of these sentences, we conducted manual or automatic adjustments, such as capitalization, punctuation fixes, etc.\n\nThe selected sentences were translated from Spanish into Catalan by a professional translation company. Subsequently, they were adapted into Valencian by an expert team from the Universitat d'Alacant.\n\nThe same corpus of sentences was translated into Galician using NOS-MT-OpenNMT-es-gl and into Basque using itzuli.\n\nA subsequent version of the corpus will include reviewed translations and source sentences.", "#### Who are the source language producers?\n\nThe Common Voice is a corpus designed for speech-related tasks. The recorded sentences are sourced from diverse origins. For more information, please refer to the project repository.", "### Annotations\n\nThis corpus doesn't have annotations.", "#### Annotation process\n\nN/A", "#### Who are the annotators?\n\nN/A", "### Personal and Sensitive Information\n\nThe original sentences are in Spanish and come from the Spanish Common Voice Corpus. To our knowledge, there are no private person’s personal identifiers or sensitive information.", "## Considerations for Using the Data", "### Social Impact of Dataset\n\nWe expect that this corpus will contribute to the development of speech technologies in the targeted languages.", "### Discussion of Biases\n\nWe are aware that some of the sentences in the corpus may convey stereotypes. Nonetheless, we have not applied any steps to reduce their impact.", "### Other Known Limitations\n\nThe translation into Galician and Basque was done through machine translation, and post-editing is required. Additionally, we have identified some errors in the source sentences. A subsequent version of the corpus will include reviewed translations and source sentences.", "## Additional Information", "### Authors\nGrupo de Procesamiento del Lenguaje Natural y Sistemas de Información, Centro de Inteligencia Digital (CENID, Universidad de Alicante),\n\nHizkuntza eta Politika Saila (Eusko Jaurlaritza),\n\nHiTZ Center - Aholab, University of the Basque Country UPV/EHU, \n\nLanguage Technologies Unit (LangTech) at the Barcelona Supercomputing Center (BSC),\n\nProxecto Nós (Universidade de Santiago de Compostela).", "### Contact information\nFor further information, please send an email to langtech@URL.", "### Copyright\nCopyright Language Technologies Unit at Barcelona Supercomputing Center (2023).", "### Licensing information\nThis work is licensed under a CC.", "### Funding\n\nThis work is funded by the Ministerio de Asuntos Económicos y Transformación Digital and Plan de Recuperación, Transformación y Resiliencia - Funded by EU – NextGenerationEU within the framework of the project ILENIA with reference 2022/TL22/00215337." ]

[ "task_categories:text-generation", "language:en", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#task_categories-text-generation #language-English #region-us \n" ]

[ "task_categories:automatic-speech-recognition", "language:es", "language:eu", "license:cc0-1.0", "region:us" ]

[]

[ "es", "eu" ]

[ "### Dataset Summary\n\n\nThe Basque Parliament Speech Corpus 1.0 consists of 1462 hours of speech extracted from\nBasque Parliament plenary sessions from 2013 to 2022. Encoded as MP3 files, the dataset\ncontains 759192 transcribed segments either spoken in Basque, Spanish or both (in\nBasque and Spanish).\n\n\nThe corpus was created to help the development of speech technology for the Basque\nlanguage, which is relatively low-resourced. However, the dataset is suited to the\ndevelopment of bilingual ASR systems, meaning to decode speech signals in Basque and/or\nSpanish. Given the similarity between Basque and Spanish at the phonetic/phonological\nlevel, acoustic models can be shared by both languages, which comes to circumvent\nthe lack of training data for Basque.\n\n\nThe dataset contains of four splits: 'train', 'train\\_clean', 'dev' and 'test', all of\nthem containing 3-10 second long speech segments and their corresponding transcriptions.\nBesides the transcription, each segment includes a speaker identifier and a language tag\n(Spanish, Basque or bilingual).\n\n\nThe 'train' split, aimed at estimating acoustic models, was extracted from 2013-2021\nsessions, amounting to 1445 hours of speech. The 'train\\_clean' split is a subset of\nthe 'train' split, containing only highly reliable transcriptions. The 'dev' and 'test'\nsplits, amounting to 7.6 and 9.6 hours of speech respectively, were extracted from\nFebruary 2022 sessions and their transcripts were manually audited.", "### Languages\n\n\nThe dataset contains segments either spoken in Basque ('eu'), Spanish ('es') or both ('bi').\nThe language distribution is strongly biased towards Spanish and bilingual segments are\nvery unfrequent.\n\n\nDuration (in hours) disaggregated per language:\n\n\n\nNumber of segments disaggregated per language:\n\n\n\nThe dataset contains four configs that can be used to select the full set of multilingual\nsegments or just a subset of them, constrained to a single language:\n\n\n* 'all' : all the segments\n* 'es' : only the Spanish segments\n* 'eu' : only the Basque segments\n* 'bi' : only the bilingual segments\n\n\nHow to use\n----------\n\n\nYou can use the 'datasets' library to load the dataset from Python. The dataset can be\ndownloaded in one call to your local drive by using the 'load\\_dataset' function. For\nexample, to download the Basque config of the 'train' split, simply specify the\ndesired language config name (i.e., \"eu\" for Basque) and the split:\n\n\nThe default config is 'all' and if no split is indicated all splits are prepared, so\nthe next code prepares the full dataset:" ]

[ "TAGS\n#task_categories-automatic-speech-recognition #language-Spanish #language-Basque #license-cc0-1.0 #region-us \n", "### Dataset Summary\n\n\nThe Basque Parliament Speech Corpus 1.0 consists of 1462 hours of speech extracted from\nBasque Parliament plenary sessions from 2013 to 2022. Encoded as MP3 files, the dataset\ncontains 759192 transcribed segments either spoken in Basque, Spanish or both (in\nBasque and Spanish).\n\n\nThe corpus was created to help the development of speech technology for the Basque\nlanguage, which is relatively low-resourced. However, the dataset is suited to the\ndevelopment of bilingual ASR systems, meaning to decode speech signals in Basque and/or\nSpanish. Given the similarity between Basque and Spanish at the phonetic/phonological\nlevel, acoustic models can be shared by both languages, which comes to circumvent\nthe lack of training data for Basque.\n\n\nThe dataset contains of four splits: 'train', 'train\\_clean', 'dev' and 'test', all of\nthem containing 3-10 second long speech segments and their corresponding transcriptions.\nBesides the transcription, each segment includes a speaker identifier and a language tag\n(Spanish, Basque or bilingual).\n\n\nThe 'train' split, aimed at estimating acoustic models, was extracted from 2013-2021\nsessions, amounting to 1445 hours of speech. The 'train\\_clean' split is a subset of\nthe 'train' split, containing only highly reliable transcriptions. The 'dev' and 'test'\nsplits, amounting to 7.6 and 9.6 hours of speech respectively, were extracted from\nFebruary 2022 sessions and their transcripts were manually audited.", "### Languages\n\n\nThe dataset contains segments either spoken in Basque ('eu'), Spanish ('es') or both ('bi').\nThe language distribution is strongly biased towards Spanish and bilingual segments are\nvery unfrequent.\n\n\nDuration (in hours) disaggregated per language:\n\n\n\nNumber of segments disaggregated per language:\n\n\n\nThe dataset contains four configs that can be used to select the full set of multilingual\nsegments or just a subset of them, constrained to a single language:\n\n\n* 'all' : all the segments\n* 'es' : only the Spanish segments\n* 'eu' : only the Basque segments\n* 'bi' : only the bilingual segments\n\n\nHow to use\n----------\n\n\nYou can use the 'datasets' library to load the dataset from Python. The dataset can be\ndownloaded in one call to your local drive by using the 'load\\_dataset' function. For\nexample, to download the Basque config of the 'train' split, simply specify the\ndesired language config name (i.e., \"eu\" for Basque) and the split:\n\n\nThe default config is 'all' and if no split is indicated all splits are prepared, so\nthe next code prepares the full dataset:" ]

[ "size_categories:1K<n<10K", "rlfh", "argilla", "human-feedback", "region:us" ]

[]

[]

[ "### Dataset Summary\n\n\nThis dataset contains:\n\n\n* A dataset configuration file conforming to the Argilla dataset format named 'URL'. This configuration file will be used to configure the dataset when using the 'FeedbackDataset.from\\_huggingface' method in Argilla.\n* Dataset records in a format compatible with HuggingFace 'datasets'. These records will be loaded automatically when using 'FeedbackDataset.from\\_huggingface' and can be loaded independently using the 'datasets' library via 'load\\_dataset'.\n* The annotation guidelines that have been used for building and curating the dataset, if they've been defined in Argilla.", "### Load with Argilla\n\n\nTo load with Argilla, you'll just need to install Argilla as 'pip install argilla --upgrade' and then use the following code:", "### Load with 'datasets'\n\n\nTo load this dataset with 'datasets', you'll just need to install 'datasets' as 'pip install datasets --upgrade' and then use the following code:", "### Supported Tasks and Leaderboards\n\n\nThis dataset can contain multiple fields, questions and responses so it can be used for different NLP tasks, depending on the configuration. The dataset structure is described in the Dataset Structure section.\n\n\nThere are no leaderboards associated with this dataset.", "### Languages\n\n\nDataset Structure\n-----------------", "### Data in Argilla\n\n\nThe dataset is created in Argilla with: fields, questions, suggestions, metadata, vectors, and guidelines.\n\n\nThe fields are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\nThe questions are the questions that will be asked to the annotators. They can be of different types, such as rating, text, label\\_selection, multi\\_label\\_selection, or ranking.\n\n\n\nThe suggestions are human or machine generated recommendations for each question to assist the annotator during the annotation process, so those are always linked to the existing questions, and named appending \"-suggestion\" and \"-suggestion-metadata\" to those, containing the value/s of the suggestion and its metadata, respectively. So on, the possible values are the same as in the table above, but the column name is appended with \"-suggestion\" and the metadata is appended with \"-suggestion-metadata\".\n\n\nThe metadata is a dictionary that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n\n\n\nThe guidelines, are optional as well, and are just a plain string that can be used to provide instructions to the annotators. Find those in the annotation guidelines section.", "### Data Instances\n\n\nAn example of a dataset instance in Argilla looks as follows:\n\n\nWhile the same record in HuggingFace 'datasets' looks as follows:", "### Data Fields\n\n\nAmong the dataset fields, we differentiate between the following:\n\n\n* Fields: These are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\t+ text is of type 'URL'.\n* Questions: These are the questions that will be asked to the annotators. They can be of different types, such as 'RatingQuestion', 'TextQuestion', 'LabelQuestion', 'MultiLabelQuestion', and 'RankingQuestion'.\n\n\n\t+ label is of type 'QuestionTypes.label\\_selection' with the following allowed values ['World', 'Sports', 'Business', 'Sci/Tech'].\n* Suggestions: As of Argilla 1.13.0, the suggestions have been included to provide the annotators with suggestions to ease or assist during the annotation process. Suggestions are linked to the existing questions, are always optional, and contain not just the suggestion itself, but also the metadata linked to it, if applicable.\n\n\n\t+ (optional) label-suggestion is of type 'QuestionTypes.label\\_selection' with the following allowed values ['World', 'Sports', 'Business', 'Sci/Tech'].\n\n\nAdditionally, we also have two more fields that are optional and are the following:\n\n\n* metadata: This is an optional field that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n* external\\_id: This is an optional field that can be used to provide an external ID for the dataset record. This can be useful if you want to link the dataset record to an external resource, such as a database or a file.", "### Data Splits\n\n\nThe dataset contains a single split, which is 'train'.\n\n\nDataset Creation\n----------------", "### Curation Rationale", "### Source Data", "#### Initial Data Collection and Normalization", "#### Who are the source language producers?", "### Annotations", "#### Annotation guidelines\n\n\nClassify the articles into one of the four categories.", "#### Annotation process", "#### Who are the annotators?", "### Personal and Sensitive Information\n\n\nConsiderations for Using the Data\n---------------------------------", "### Social Impact of Dataset", "### Discussion of Biases", "### Other Known Limitations\n\n\nAdditional Information\n----------------------", "### Dataset Curators", "### Licensing Information", "### Contributions" ]

[ "TAGS\n#size_categories-1K<n<10K #rlfh #argilla #human-feedback #region-us \n", "### Dataset Summary\n\n\nThis dataset contains:\n\n\n* A dataset configuration file conforming to the Argilla dataset format named 'URL'. This configuration file will be used to configure the dataset when using the 'FeedbackDataset.from\\_huggingface' method in Argilla.\n* Dataset records in a format compatible with HuggingFace 'datasets'. These records will be loaded automatically when using 'FeedbackDataset.from\\_huggingface' and can be loaded independently using the 'datasets' library via 'load\\_dataset'.\n* The annotation guidelines that have been used for building and curating the dataset, if they've been defined in Argilla.", "### Load with Argilla\n\n\nTo load with Argilla, you'll just need to install Argilla as 'pip install argilla --upgrade' and then use the following code:", "### Load with 'datasets'\n\n\nTo load this dataset with 'datasets', you'll just need to install 'datasets' as 'pip install datasets --upgrade' and then use the following code:", "### Supported Tasks and Leaderboards\n\n\nThis dataset can contain multiple fields, questions and responses so it can be used for different NLP tasks, depending on the configuration. The dataset structure is described in the Dataset Structure section.\n\n\nThere are no leaderboards associated with this dataset.", "### Languages\n\n\nDataset Structure\n-----------------", "### Data in Argilla\n\n\nThe dataset is created in Argilla with: fields, questions, suggestions, metadata, vectors, and guidelines.\n\n\nThe fields are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\nThe questions are the questions that will be asked to the annotators. They can be of different types, such as rating, text, label\\_selection, multi\\_label\\_selection, or ranking.\n\n\n\nThe suggestions are human or machine generated recommendations for each question to assist the annotator during the annotation process, so those are always linked to the existing questions, and named appending \"-suggestion\" and \"-suggestion-metadata\" to those, containing the value/s of the suggestion and its metadata, respectively. So on, the possible values are the same as in the table above, but the column name is appended with \"-suggestion\" and the metadata is appended with \"-suggestion-metadata\".\n\n\nThe metadata is a dictionary that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n\n\n\nThe guidelines, are optional as well, and are just a plain string that can be used to provide instructions to the annotators. Find those in the annotation guidelines section.", "### Data Instances\n\n\nAn example of a dataset instance in Argilla looks as follows:\n\n\nWhile the same record in HuggingFace 'datasets' looks as follows:", "### Data Fields\n\n\nAmong the dataset fields, we differentiate between the following:\n\n\n* Fields: These are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\t+ text is of type 'URL'.\n* Questions: These are the questions that will be asked to the annotators. They can be of different types, such as 'RatingQuestion', 'TextQuestion', 'LabelQuestion', 'MultiLabelQuestion', and 'RankingQuestion'.\n\n\n\t+ label is of type 'QuestionTypes.label\\_selection' with the following allowed values ['World', 'Sports', 'Business', 'Sci/Tech'].\n* Suggestions: As of Argilla 1.13.0, the suggestions have been included to provide the annotators with suggestions to ease or assist during the annotation process. Suggestions are linked to the existing questions, are always optional, and contain not just the suggestion itself, but also the metadata linked to it, if applicable.\n\n\n\t+ (optional) label-suggestion is of type 'QuestionTypes.label\\_selection' with the following allowed values ['World', 'Sports', 'Business', 'Sci/Tech'].\n\n\nAdditionally, we also have two more fields that are optional and are the following:\n\n\n* metadata: This is an optional field that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n* external\\_id: This is an optional field that can be used to provide an external ID for the dataset record. This can be useful if you want to link the dataset record to an external resource, such as a database or a file.", "### Data Splits\n\n\nThe dataset contains a single split, which is 'train'.\n\n\nDataset Creation\n----------------", "### Curation Rationale", "### Source Data", "#### Initial Data Collection and Normalization", "#### Who are the source language producers?", "### Annotations", "#### Annotation guidelines\n\n\nClassify the articles into one of the four categories.", "#### Annotation process", "#### Who are the annotators?", "### Personal and Sensitive Information\n\n\nConsiderations for Using the Data\n---------------------------------", "### Social Impact of Dataset", "### Discussion of Biases", "### Other Known Limitations\n\n\nAdditional Information\n----------------------", "### Dataset Curators", "### Licensing Information", "### Contributions" ]

[ "region:us" ]

[]

[]

[ "## The news lens:\nStart from:\nGender、tech" ]

[ "TAGS\n#region-us \n", "## The news lens:\nStart from:\nGender、tech" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"vsums_synthetic_gpt4_peudolabeled\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"vsums_synthetic_gpt4_peudolabeled\"\n\nMore Information needed" ]

[ "license:cc-by-nc-nd-4.0", "region:us" ]

[]

[]

[ "# Chest X-ray\n\nThe dataset consists of .dcm files containing X-ray images of the thorax. The images are labeled by the doctors and accompanied by corresponding annotations in JSON format. The annotations provide detailed information about the organ structures present in the chest X-ray images. \n\n![](URL", "# For Commercial Usage: Full version of the dataset includes 400+ chest x-rays of people with different conditions, leave a request on TrainingData to buy the dataset", "### Types of diseases and conditions in the dataset:\n- Petrifications\n- Nodule/mass \n- Infiltration/Consolidation \n- Fibrosis\n- Dissemination \n- Pleural effusion\n- Hilar enlargement \n- Annular shadows \n- Healed rib fracture \n- Enlarged medinastium \n- Rib fractures \n- Pneumothorax\n- Atelectasis", "## Statistics for the dataset:\n\n![](URL\n\nThe dataset aims to aid in the development and evaluation of algorithms for automated detection and classification of thoracic organ abnormalities and diseases. \n\nThe dataset is valuable for research in neurology, radiology, and oncology. It allows the development and evaluation of computer-based algorithms, machine learning models, and deep learning techniques for automated detection, diagnosis, and classification of these conditions.", "# Buy the Dataset: This is just an example of the data. Leave a request on URL to discuss your requirements, learn about the price and buy the dataset", "# Content", "### The dataset includes:\n- files: includes x-ray scans in .dcm format,\n- annotations: includes annotations in JSON format made for files in the previous folder,\n- visualizations: includes visualizations of the annotations,\n- .csv file: includes links to the fies and metadata", "### File with the extension .csv includes the following information for each media file:\n\n- dcm_path: link to access the .dcm file,\n- annotation_path: link to access the file with annotation in JSON-format,\n- age: age of the person in the x-ray scan,\n- sex: gender of the person in the x-ray scan,\n- StudyInstanceUID: id of the study,\n- Nodule/mass: wheter nodule/mass is observed,\n- Dissemination: wheter dissemination is observed,\n- Annular shadows: wheter annular shadows are observed,\n- Petrifications: wheter petrifications are observed,\n- Pleural effusion: wheter pleural effusion is observed", "# Medical data might be collected in accordance with your requirements.", "## TrainingData provides high-quality data annotation tailored to your needs\n\nMore datasets in TrainingData's Kaggle account: <URL\n\nTrainingData's GitHub: URL\n\n*keywords: ibeta level 1, ibeta level 2, liveness detection systems, liveness detection dataset, biometric dataset, biometric data dataset, biometric system attacks, anti-spoofing dataset, face liveness detection, deep learning dataset, face spoofing database, face anti-spoofing, face recognition, face detection, face identification, human video dataset, video dataset, presentation attack detection, presentation attack dataset, 2d print attacks, print 2d attacks dataset, printed 2d masks dataset, spoofing in 2D face recognition, facial masks, 2D face recognition systems, detecting face spoofing attacks, detecting presentation attacks, computer vision, surveillance face anti-spoofing, face liveness detection software solution, silicone masks attacks*" ]

[ "TAGS\n#license-cc-by-nc-nd-4.0 #region-us \n", "# Chest X-ray\n\nThe dataset consists of .dcm files containing X-ray images of the thorax. The images are labeled by the doctors and accompanied by corresponding annotations in JSON format. The annotations provide detailed information about the organ structures present in the chest X-ray images. \n\n![](URL", "# For Commercial Usage: Full version of the dataset includes 400+ chest x-rays of people with different conditions, leave a request on TrainingData to buy the dataset", "### Types of diseases and conditions in the dataset:\n- Petrifications\n- Nodule/mass \n- Infiltration/Consolidation \n- Fibrosis\n- Dissemination \n- Pleural effusion\n- Hilar enlargement \n- Annular shadows \n- Healed rib fracture \n- Enlarged medinastium \n- Rib fractures \n- Pneumothorax\n- Atelectasis", "## Statistics for the dataset:\n\n![](URL\n\nThe dataset aims to aid in the development and evaluation of algorithms for automated detection and classification of thoracic organ abnormalities and diseases. \n\nThe dataset is valuable for research in neurology, radiology, and oncology. It allows the development and evaluation of computer-based algorithms, machine learning models, and deep learning techniques for automated detection, diagnosis, and classification of these conditions.", "# Buy the Dataset: This is just an example of the data. Leave a request on URL to discuss your requirements, learn about the price and buy the dataset", "# Content", "### The dataset includes:\n- files: includes x-ray scans in .dcm format,\n- annotations: includes annotations in JSON format made for files in the previous folder,\n- visualizations: includes visualizations of the annotations,\n- .csv file: includes links to the fies and metadata", "### File with the extension .csv includes the following information for each media file:\n\n- dcm_path: link to access the .dcm file,\n- annotation_path: link to access the file with annotation in JSON-format,\n- age: age of the person in the x-ray scan,\n- sex: gender of the person in the x-ray scan,\n- StudyInstanceUID: id of the study,\n- Nodule/mass: wheter nodule/mass is observed,\n- Dissemination: wheter dissemination is observed,\n- Annular shadows: wheter annular shadows are observed,\n- Petrifications: wheter petrifications are observed,\n- Pleural effusion: wheter pleural effusion is observed", "# Medical data might be collected in accordance with your requirements.", "## TrainingData provides high-quality data annotation tailored to your needs\n\nMore datasets in TrainingData's Kaggle account: <URL\n\nTrainingData's GitHub: URL\n\n*keywords: ibeta level 1, ibeta level 2, liveness detection systems, liveness detection dataset, biometric dataset, biometric data dataset, biometric system attacks, anti-spoofing dataset, face liveness detection, deep learning dataset, face spoofing database, face anti-spoofing, face recognition, face detection, face identification, human video dataset, video dataset, presentation attack detection, presentation attack dataset, 2d print attacks, print 2d attacks dataset, printed 2d masks dataset, spoofing in 2D face recognition, facial masks, 2D face recognition systems, detecting face spoofing attacks, detecting presentation attacks, computer vision, surveillance face anti-spoofing, face liveness detection software solution, silicone masks attacks*" ]

[ "region:us" ]

[]

[]

[ "# Code for paper \"Evaluation of a digital ophthalmologist app built by GPT-4V(ision)\"", "# Images used in this dataset are available by contacting with the corresponding author." ]

[ "TAGS\n#region-us \n", "# Code for paper \"Evaluation of a digital ophthalmologist app built by GPT-4V(ision)\"", "# Images used in this dataset are available by contacting with the corresponding author." ]

[ "language:en", "kinematic research", "XR user motions", "VR user motions", "AR user motions", "motions", "arxiv:2306.03381", "region:us" ]

[ "2306.03381" ]

[ "en" ]

[ "# XR Motion Dataset Catalogue", "## Overview\n\nThe XR Motion Dataset Catalogue, accompanying our paper \"Navigating the Kinematic Maze: A Comprehensive Guide to XR Motion Dataset Standards,\" standardizes and simplifies access to Extended Reality (XR) motion datasets. The catalogue represents our initiative to streamline the usage of kinematic data in XR research by aligning various datasets to a consistent format and structure.", "### Dataset Specifications\nAll datasets in this catalogue have been standardized with the following specifications:\n- Coordinate System: X (Right), Y (Up), Z (Forward)\n- Rotation Representation: Quaternions\n- Units of Measurement: Centimeters for spatial data\n- Time Encoding: Milliseconds for time-related data\n\nThese specifications ensure uniformity and comparability across all datasets in the catalogue.", "### Conversion Scripts Repository\nThe alignment of datasets was facilitated by a series of conversion scripts, which are available in our GitHub repository: XR Motion Dataset Conversion Scripts. These scripts detail the process of aligning attribute names, coordinate systems, rotation representations, units of measurement, and time encoding.", "### Included Datasets\nThe catalogue includes the following datasets:\n1. LiebersBeatSaber23\n2. Boxrr23 – *currently, only a small subset is available*\n3. LiebersHand22\n4. LiebersLabStudy21\n5. MooreCrossDomain23\n6. <del>RMillerBall22</del> *request for permissions pending*\n7. VrNet\n8. WhoIsAlyx", "## Installation and Usage", "### Loading the Dataset with Hugging Face 'datasets' Library\nTo load a dataset from the catalogue, use the 'datasets' library in Python. For example, to load the 'WhoIsAlyx' dataset:", "### Loading Individual Recordings with Pandas\nTo load individual recordings, you can use 'pandas'. Here's an example:", "## Contributing and Feedback\nContributions and feedback are welcome to enhance the XR Motion Dataset Catalogue. Feel free to open a pull request or contact us directly." ]

[ "TAGS\n#language-English #kinematic research #XR user motions #VR user motions #AR user motions #motions #arxiv-2306.03381 #region-us \n", "# XR Motion Dataset Catalogue", "## Overview\n\nThe XR Motion Dataset Catalogue, accompanying our paper \"Navigating the Kinematic Maze: A Comprehensive Guide to XR Motion Dataset Standards,\" standardizes and simplifies access to Extended Reality (XR) motion datasets. The catalogue represents our initiative to streamline the usage of kinematic data in XR research by aligning various datasets to a consistent format and structure.", "### Dataset Specifications\nAll datasets in this catalogue have been standardized with the following specifications:\n- Coordinate System: X (Right), Y (Up), Z (Forward)\n- Rotation Representation: Quaternions\n- Units of Measurement: Centimeters for spatial data\n- Time Encoding: Milliseconds for time-related data\n\nThese specifications ensure uniformity and comparability across all datasets in the catalogue.", "### Conversion Scripts Repository\nThe alignment of datasets was facilitated by a series of conversion scripts, which are available in our GitHub repository: XR Motion Dataset Conversion Scripts. These scripts detail the process of aligning attribute names, coordinate systems, rotation representations, units of measurement, and time encoding.", "### Included Datasets\nThe catalogue includes the following datasets:\n1. LiebersBeatSaber23\n2. Boxrr23 – *currently, only a small subset is available*\n3. LiebersHand22\n4. LiebersLabStudy21\n5. MooreCrossDomain23\n6. <del>RMillerBall22</del> *request for permissions pending*\n7. VrNet\n8. WhoIsAlyx", "## Installation and Usage", "### Loading the Dataset with Hugging Face 'datasets' Library\nTo load a dataset from the catalogue, use the 'datasets' library in Python. For example, to load the 'WhoIsAlyx' dataset:", "### Loading Individual Recordings with Pandas\nTo load individual recordings, you can use 'pandas'. Here's an example:", "## Contributing and Feedback\nContributions and feedback are welcome to enhance the XR Motion Dataset Catalogue. Feel free to open a pull request or contact us directly." ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"rap_phase2_11jan_15i_v2\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"rap_phase2_11jan_15i_v2\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"rap_phase2_11jan_15i_v3\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"rap_phase2_11jan_15i_v3\"\n\nMore Information needed" ]

[ "license:unlicense", "UNA", "DPO", "ULMA", "region:us" ]

[]

[]

[ "### DPO Training Set (Target Character and Persona)\n\n1. Define Character and Persona:\n Precisely define the traits, behaviors, and speech patterns of the intended character and persona, including language style, tone, typical responses, and unique characteristics.\n\n2. Dataset Construction:\n Develop a dataset that reflects these characteristics through dialogues, monologues, and interactions typical of the persona. Ensure the dataset's diversity to encompass various scenarios and responses.\n\n3. Annotation:\n Label each dataset instance with preference scores or binary labels, indicating its alignment with the target persona for effective DPO implementation.", "### UNA Training Set (Neutralizing Extremes)\n\n1. Identify Extremes:\n Identify extreme positive or negative sentiments in the context of your character, such as overly aggressive or excessively submissive language.\n\n2. Neutral Dataset:\n Build a dataset representing neutral interactions and responses, focusing on language and replies that are balanced and free from identified extremes.\n\n3. Annotation for Neutrality:\n Annotate the dataset to promote a neutral, balanced language style, possibly employing a point-wise preference approach similar to DPO.", "### Training and Merging Models\n\n1. Train Separate Models:\n Train one model using the DPO dataset and subsequently realign it using the UNA dataset. Each model will learn distinct aspects: character alignment and neutralization of extremes.\n\n2. Merging Models:\n Combining two independently trained models into a single unified model is complex and often requires sophisticated techniques and deep understanding of model architectures. For this, we employ the 'LazyMergeKit'.\n\n3. Evaluation and Adjustment:\n Post-merging, assess the unified model to verify if it achieves the intended balance. Iterative refinement of the training datasets and merging process might be necessary based on evaluation outcomes." ]

[ "TAGS\n#license-unlicense #UNA #DPO #ULMA #region-us \n", "### DPO Training Set (Target Character and Persona)\n\n1. Define Character and Persona:\n Precisely define the traits, behaviors, and speech patterns of the intended character and persona, including language style, tone, typical responses, and unique characteristics.\n\n2. Dataset Construction:\n Develop a dataset that reflects these characteristics through dialogues, monologues, and interactions typical of the persona. Ensure the dataset's diversity to encompass various scenarios and responses.\n\n3. Annotation:\n Label each dataset instance with preference scores or binary labels, indicating its alignment with the target persona for effective DPO implementation.", "### UNA Training Set (Neutralizing Extremes)\n\n1. Identify Extremes:\n Identify extreme positive or negative sentiments in the context of your character, such as overly aggressive or excessively submissive language.\n\n2. Neutral Dataset:\n Build a dataset representing neutral interactions and responses, focusing on language and replies that are balanced and free from identified extremes.\n\n3. Annotation for Neutrality:\n Annotate the dataset to promote a neutral, balanced language style, possibly employing a point-wise preference approach similar to DPO.", "### Training and Merging Models\n\n1. Train Separate Models:\n Train one model using the DPO dataset and subsequently realign it using the UNA dataset. Each model will learn distinct aspects: character alignment and neutralization of extremes.\n\n2. Merging Models:\n Combining two independently trained models into a single unified model is complex and often requires sophisticated techniques and deep understanding of model architectures. For this, we employ the 'LazyMergeKit'.\n\n3. Evaluation and Adjustment:\n Post-merging, assess the unified model to verify if it achieves the intended balance. Iterative refinement of the training datasets and merging process might be necessary based on evaluation outcomes." ]

[ "license:cc-by-4.0", "region:us" ]

[]

[]

[ "# LitBank\n\n- Project: URL\n- Data source: URL\n- Crossval splits source: URL", "## Details\n\nTen configs of the form f\"split_{X}\" where X is in range(10)", "### Features", "### Event detection", "### Coreference" ]

[ "TAGS\n#license-cc-by-4.0 #region-us \n", "# LitBank\n\n- Project: URL\n- Data source: URL\n- Crossval splits source: URL", "## Details\n\nTen configs of the form f\"split_{X}\" where X is in range(10)", "### Features", "### Event detection", "### Coreference" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"rap_phase2_11jan_15i_v4\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"rap_phase2_11jan_15i_v4\"\n\nMore Information needed" ]

[ "license:mit", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-mit #region-us \n" ]

[ "license:apache-2.0", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-apache-2.0 #region-us \n" ]

[ "license:other", "region:us" ]

[]

[]

[ "# Our 33B-v1.1 model is now live (We'll always be serving the newest model on our web app)!\n33B-v1.1 model comes with a \"Prompt Enhancement\" feature. Access at: URL", "# Our Discord Server\nJoin us at: URL (Updated on Dec 29th. Now permanent link to join)", "# Apache-2.0 + WhiteRabbitNeo Extended Version", "# Licence: Usage Restrictions" ]

[ "TAGS\n#license-other #region-us \n", "# Our 33B-v1.1 model is now live (We'll always be serving the newest model on our web app)!\n33B-v1.1 model comes with a \"Prompt Enhancement\" feature. Access at: URL", "# Our Discord Server\nJoin us at: URL (Updated on Dec 29th. Now permanent link to join)", "# Apache-2.0 + WhiteRabbitNeo Extended Version", "# Licence: Usage Restrictions" ]

[ "license:apache-2.0", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-apache-2.0 #region-us \n" ]

[ "task_categories:text-generation", "task_categories:image-to-text", "task_categories:text-to-image", "annotations_creators:machine-generated", "size_categories:n<650k", "source_datasets:mscoco", "language:en", "coco", "mscoco", "simple-english", "arxiv:1405.0312", "region:us" ]

[ "1405.0312" ]

[ "en" ]

[ "### Dataset Description\n\n\n* Curated by: {{ curators | default(\"\", true)}}\n* Language(s) (NLP): {{ language | default(\"\", true)}}\n* License: {{ license | default(\"\", true)}}", "### Dataset Sources\n\n\nThe processed MS COCO datasets (Karpathy Split) in this repo are based on the following sources:\n\n\nType: Train, MD5: aa31ac474cf6250ebb81d18348a07ed8, URL: URL\nType: Validation, MD5: b273847456ef5580e33713b1f7de52a0, URL: URL\nType: Test, MD5: 3ff34b0ef2db02d01c37399f6a2a6cd1, URL: URL\n\n\nMS COCO:\n\n\n* Download: URL\n* Paper: URL\n\n\nDataset Creation\n----------------\n\n\nThis dataset was generated by processing the annotations via Mistal7B.\n\n\nPrompt used:\n\n\nA filter was applied to only store captions which matched the common output format. A best effort filter was applied to reduce the chance of including multiple example sentences in the output.", "### Curation Rationale\n\n\nThis dataset is useful for experiments with small LLMs which have only a reduced corpus. The dataset is suitable to be used for LAVIS experiments (QFormer Training) with a finetuned TinyStories 33M LLM." ]

[ "TAGS\n#task_categories-text-generation #task_categories-image-to-text #task_categories-text-to-image #annotations_creators-machine-generated #size_categories-n<650k #source_datasets-mscoco #language-English #coco #mscoco #simple-english #arxiv-1405.0312 #region-us \n", "### Dataset Description\n\n\n* Curated by: {{ curators | default(\"\", true)}}\n* Language(s) (NLP): {{ language | default(\"\", true)}}\n* License: {{ license | default(\"\", true)}}", "### Dataset Sources\n\n\nThe processed MS COCO datasets (Karpathy Split) in this repo are based on the following sources:\n\n\nType: Train, MD5: aa31ac474cf6250ebb81d18348a07ed8, URL: URL\nType: Validation, MD5: b273847456ef5580e33713b1f7de52a0, URL: URL\nType: Test, MD5: 3ff34b0ef2db02d01c37399f6a2a6cd1, URL: URL\n\n\nMS COCO:\n\n\n* Download: URL\n* Paper: URL\n\n\nDataset Creation\n----------------\n\n\nThis dataset was generated by processing the annotations via Mistal7B.\n\n\nPrompt used:\n\n\nA filter was applied to only store captions which matched the common output format. A best effort filter was applied to reduce the chance of including multiple example sentences in the output.", "### Curation Rationale\n\n\nThis dataset is useful for experiments with small LLMs which have only a reduced corpus. The dataset is suitable to be used for LAVIS experiments (QFormer Training) with a finetuned TinyStories 33M LLM." ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.", "## Dataset Details", "### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:", "### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### 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\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Dataset Card Authors [optional]", "## Dataset Card Contact" ]

[ "TAGS\n#region-us \n", "# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.", "## Dataset Details", "### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:", "### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### 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\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Dataset Card Authors [optional]", "## Dataset Card Contact" ]

[ "arxiv:1705.03551", "region:us" ]

[ "1705.03551" ]

[]

[ "# Dataset Card for \"trivia_qa\"\n\nA processed version of this Trivia QA dataset. Here is the original paper.\n\n* Our 'test' set consists of the validation set of the unfiltered subset.\n* Our 'train' set consists of the training, validation, and test of the rc subset.\n\nThe 'evidence' column includes a document that support the answer to the question." ]

[ "TAGS\n#arxiv-1705.03551 #region-us \n", "# Dataset Card for \"trivia_qa\"\n\nA processed version of this Trivia QA dataset. Here is the original paper.\n\n* Our 'test' set consists of the validation set of the unfiltered subset.\n* Our 'train' set consists of the training, validation, and test of the rc subset.\n\nThe 'evidence' column includes a document that support the answer to the question." ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "task_categories:conversational", "task_categories:text-generation", "language:en", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#task_categories-conversational #task_categories-text-generation #language-English #region-us \n" ]

[ "license:wtfpl", "region:us" ]

[]

[]

[ "# Interpreting the data\n- b0/b1\n: Internationalism/Nationalism\n- c0/c1\n: Constructivism/Essentialism\n- e0/e1\n: Ecology/Production\n- j0/j1\n: Rehabilitative Justice/Punitive Justice\n- m0/m1\n: Regulation/Laissez-faire\n- p0/p1\n: Communism/Capitalism\n- s0/s1\n: Progressive/Conservative\n- t0/t1\n: Revolution/Reform\n- reli\n: Religiousness\n- comp\n: Belief in a worldwide conspiracy\n- prag\n: Pragmatism\n- mona\n: Monarchism\n- vega\n: VEGAN\n- anar\n: Anarchism\n- femi:\n: Radical feminism", "### Suggestions for calculations\n- Whackiness of the model=anar+comp+mona+reli\n- Certainty=(x0+x1), calculate average of all values\n- Bias towards value(logratio)=LOG(x0/x1;2)\n- Left-right bias=b_logratio+c_logratio+e_logratio+j_logratio+m_logratio+p_logratio+s_logratio-t_logratio", "# Results\n!URL\n- Mixtral-instruct0.1 hates violence(-3.1 logratio_t!!!), religion(0.4%), pragmatic politics(1.4%), monarchy(0.6%), anarchy(5.7%) and conspiracy theories(0.2%); likes regulation(1.5 logratio_t), globalism(1.4) and ecology(0.64). The MOST vegan(72%!!!) model tested so far. EXTREME left-wing bias.\n- LLAMA2-70b is fairly neutral, with slight bias to the left.\n- Dicephal-123(self-merge of llama2-70B) is also fairly neutral, with slight bias to the right. Sadly, it is the most right-wing model that I tested.\n- Xwin, Goliath, Nous-Hermes have low left-wing bias.\n- DoubleGold and WinterGoliath have medium left-wing bias.\n- WinterGoddess and Euryale have high left-wing bias.\n\n\nMy suspicions were correct, WinterGoliath has stronger left wing bias than Goliath and is less whacky, I cannot consider it an upgrade, just a sidegrade.", "# Limitations\nThe tests were done without any special prompting. How models perform on the test does not reflect how they perform with the right prompting, it just shows the bias of the model.\n\nThis test does NOT measure censorship." ]

[ "TAGS\n#license-wtfpl #region-us \n", "# Interpreting the data\n- b0/b1\n: Internationalism/Nationalism\n- c0/c1\n: Constructivism/Essentialism\n- e0/e1\n: Ecology/Production\n- j0/j1\n: Rehabilitative Justice/Punitive Justice\n- m0/m1\n: Regulation/Laissez-faire\n- p0/p1\n: Communism/Capitalism\n- s0/s1\n: Progressive/Conservative\n- t0/t1\n: Revolution/Reform\n- reli\n: Religiousness\n- comp\n: Belief in a worldwide conspiracy\n- prag\n: Pragmatism\n- mona\n: Monarchism\n- vega\n: VEGAN\n- anar\n: Anarchism\n- femi:\n: Radical feminism", "### Suggestions for calculations\n- Whackiness of the model=anar+comp+mona+reli\n- Certainty=(x0+x1), calculate average of all values\n- Bias towards value(logratio)=LOG(x0/x1;2)\n- Left-right bias=b_logratio+c_logratio+e_logratio+j_logratio+m_logratio+p_logratio+s_logratio-t_logratio", "# Results\n!URL\n- Mixtral-instruct0.1 hates violence(-3.1 logratio_t!!!), religion(0.4%), pragmatic politics(1.4%), monarchy(0.6%), anarchy(5.7%) and conspiracy theories(0.2%); likes regulation(1.5 logratio_t), globalism(1.4) and ecology(0.64). The MOST vegan(72%!!!) model tested so far. EXTREME left-wing bias.\n- LLAMA2-70b is fairly neutral, with slight bias to the left.\n- Dicephal-123(self-merge of llama2-70B) is also fairly neutral, with slight bias to the right. Sadly, it is the most right-wing model that I tested.\n- Xwin, Goliath, Nous-Hermes have low left-wing bias.\n- DoubleGold and WinterGoliath have medium left-wing bias.\n- WinterGoddess and Euryale have high left-wing bias.\n\n\nMy suspicions were correct, WinterGoliath has stronger left wing bias than Goliath and is less whacky, I cannot consider it an upgrade, just a sidegrade.", "# Limitations\nThe tests were done without any special prompting. How models perform on the test does not reflect how they perform with the right prompting, it just shows the bias of the model.\n\nThis test does NOT measure censorship." ]

[ "task_categories:conversational", "task_categories:text-generation", "size_categories:1M<n<10M", "region:us" ]

[]

[]

[ "## Possible improvement\n\nCurrently, the dataset contains mainly english samples. It could be nice if we can add / translate some samples into other languages !" ]

[ "TAGS\n#task_categories-conversational #task_categories-text-generation #size_categories-1M<n<10M #region-us \n", "## Possible improvement\n\nCurrently, the dataset contains mainly english samples. It could be nice if we can add / translate some samples into other languages !" ]

[ "region:us" ]

[]

[]

[ "# A new face foregery detection dataset based on FaceForensics++.\n\n4 modern face manipulation method:\n\n- inswapper\n- simswap\n- realiable faceswap\n- MCNet (face reenactment)\n\n- enhanced testset with diffusion" ]

[ "TAGS\n#region-us \n", "# A new face foregery detection dataset based on FaceForensics++.\n\n4 modern face manipulation method:\n\n- inswapper\n- simswap\n- realiable faceswap\n- MCNet (face reenactment)\n\n- enhanced testset with diffusion" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.", "## Dataset Details", "### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:", "### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### 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\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Dataset Card Authors [optional]", "## Dataset Card Contact" ]

[ "TAGS\n#region-us \n", "# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.", "## Dataset Details", "### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:", "### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### 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\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Dataset Card Authors [optional]", "## Dataset Card Contact" ]