Datasets:

---

ftopal

/

huggingface-datasets

like 0

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "## Cria-SFT-v1 is a collection of the following datasets\n- Datasets:\n - VMware/open-instruct\n - LDJnr/Capybara\n - cognitivecomputations/ultrachat-uncensored\n - starfishmedical/webGPT_x_dolly\n - THUDM/webglm-qa", "## Prompt Format" ]

[ "TAGS\n#region-us \n", "## Cria-SFT-v1 is a collection of the following datasets\n- Datasets:\n - VMware/open-instruct\n - LDJnr/Capybara\n - cognitivecomputations/ultrachat-uncensored\n - starfishmedical/webGPT_x_dolly\n - THUDM/webglm-qa", "## Prompt Format" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_BNG_waveform_5000_\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_BNG_waveform_5000_\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c3_1000_25\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c3_1000_25\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c4_1000_100\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c4_1000_100\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c4_1000_25\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c4_1000_25\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_bank8FM\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_bank8FM\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c1_1000_5\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c1_1000_5\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_puma32H\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_puma32H\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c3_1000_10\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c3_1000_10\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c4_1000_10\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c4_1000_10\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c4_1000_50\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c4_1000_50\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c0_1000_5\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c0_1000_5\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c3_1000_50\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c3_1000_50\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_kin8nm\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_kin8nm\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c3_1000_5\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c3_1000_5\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_puma8NH\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_puma8NH\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_bank32nh\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_bank32nh\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c1_1000_50\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c1_1000_50\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_house_8L\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_house_8L\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c0_1000_10\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c0_1000_10\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c0_1000_25\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c0_1000_25\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c2_1000_50\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c2_1000_50\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c2_1000_25\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c2_1000_25\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c0_1000_50\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c0_1000_50\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c1_1000_10\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c1_1000_10\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c2_1000_5\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c2_1000_5\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c2_1000_10\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c2_1000_10\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_fri_c1_1000_25\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_fri_c1_1000_25\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_mozilla4\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_mozilla4\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_pc3\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_pc3\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"metatree_pc1\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"metatree_pc1\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[]

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

[ "task_categories:image-to-image", "size_categories:n<1K", "language:en", "license:apache-2.0", "region:us" ]

[]

[ "en" ]

[ "# Dataset Card for pokemon-images-dataset", "### Dataset Summary\n\nA collection of images featuring Pokémon characters.", "## Dataset Creation", "### Context\n\nI collected this dataset for my school project. The project is to train GAN to generate new Pokemon. I had a difficult time finding a training dataset that is complete and clean. So I gather this collection of images and publish it here hoping that it will help others who need a similar dataset.\n\nYou can find my project on my [Github][1]\nMy latest code to generate pokemon [Github][4]", "### Content\n\n819 transparent Pokemon images in png format size 256x256.\n\n* Update August 10, 2020\n819 white background in jpg format", "### Acknowledgements\n\nI collected the image mostly from this website [URL\n\nBanner image is taken from [URL", "### Inspiration\n\nSince I failed to generate new Pokemon with clarity (I can only generate the shape) I wish there will be others that could do it with this dataset. If you managed to, please share it!\n\n\n [1]: URL\n [2]: URL\n [3]: URL\n [4]: URL" ]

[ "TAGS\n#task_categories-image-to-image #size_categories-n<1K #language-English #license-apache-2.0 #region-us \n", "# Dataset Card for pokemon-images-dataset", "### Dataset Summary\n\nA collection of images featuring Pokémon characters.", "## Dataset Creation", "### Context\n\nI collected this dataset for my school project. The project is to train GAN to generate new Pokemon. I had a difficult time finding a training dataset that is complete and clean. So I gather this collection of images and publish it here hoping that it will help others who need a similar dataset.\n\nYou can find my project on my [Github][1]\nMy latest code to generate pokemon [Github][4]", "### Content\n\n819 transparent Pokemon images in png format size 256x256.\n\n* Update August 10, 2020\n819 white background in jpg format", "### Acknowledgements\n\nI collected the image mostly from this website [URL\n\nBanner image is taken from [URL", "### Inspiration\n\nSince I failed to generate new Pokemon with clarity (I can only generate the shape) I wish there will be others that could do it with this dataset. If you managed to, please share it!\n\n\n [1]: URL\n [2]: URL\n [3]: URL\n [4]: URL" ]

[ "size_categories:1M<n<10M", "language:en", "license:mit", "region:us" ]

[]

[ "en" ]

[ "## Credits:\n\nThis dataset was generated from the first 1M entries of URL" ]

[ "TAGS\n#size_categories-1M<n<10M #language-English #license-mit #region-us \n", "## Credits:\n\nThis dataset was generated from the first 1M entries of URL" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"high_vs_random_min_len_100\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"high_vs_random_min_len_100\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"high_vs_random_min_len_1000\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"high_vs_random_min_len_1000\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"target-locations-0.2split\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"target-locations-0.2split\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"target-locations-0.3split\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"target-locations-0.3split\"\n\nMore Information needed" ]

[ "language:en", "language:zh", "license:mit", "arxiv:2402.05136", "region:us" ]

[ "2402.05136" ]

[ "en", "zh" ]

[ "#### Quick Start\n\n\nOur dataset evaluates the long-text capabilities of the large language models from multiple perspectives. Each subset has different length divisions, so please add a length limit when loading the dataset.", "#### Loading Data\n\n\nIf you want to download the data for hotpotwikiqa\\_mixup, you can visit this link.\nIf you need other subsets of data, simply change the zip file name in the link above.", "#### Data Format\n\n\nAll data in LV-Eval follows the following format. For certain datasets (\"loogle\\_SD\\_mixup,\" \"loogle\\_CR\\_mixup,\" \"loogle\\_MIR\\_mixup\"), there is an additional key called \"answer\\_keywords\". This key indicates the most crucial word or sentence in the answer. During the evaluation of predicted values, if the match between the prediction and the \"answer\\_keywords\" falls below a certain threshold, it directly returns 0. Otherwise, it compares the \"answers\" list with the predicted value.\n\n\nFor some datasets (\"factrecall\\_en,\" \"factrecall\\_zh,\" \"cmrc\\_mixup\"), there is an extra key called \"confusing\\_facts\". This key represents confounding elements added to increase the benchmark difficulty and has been randomly placed within long texts.\n\n\nFor certain datasets (\"hotpotwikiqa\\_mixup,\" \"multifieldqa\\_en\\_mixup,\" \"multifieldqa\\_zh\\_mixup,\" \"lic\\_mixup\"), both \"answer\\_keywords\" and \"confusing\\_facts\" are present.", "#### Evaluation\n\n\nThis repository provides data download for LV-Eval. If you wish to use this dataset for automated evaluation, please refer to our github.\n\n\nTask statistics\n===============\n\n\n\nThe abbreviations for CFI, KPR, AK represent for confusing fact insertion, keyword and phrase replacement, and answer keywords, respectively. The confusing fact insertion has already been inserted into the context and will be displayed in the jsonl file as \"confusing\\_facts\". The answer keywords will be shown in the form of \"answer\\_keywords\" in the jsonl file.\n\n\nTask construction\n=================", "### Multi-hop QA\n\n\nIn a multi-hop QA task, the reasoning process to derive the answer need to gather multiple pieces of information from various locations in the context.\n\n\n* lic-mixup is originated from the Long-instruction-en2zh dataset on Hugging Face. The original Long-instruction-en2zh contains 8,000+ high-quality Chinese multi-doc QA data translated from English. We selected 197 QA pairs and their corresponding documents as supporting data, while the remaining documents serve as distracting data for context mixing.\n* hotpotwikiqa-mixup is originated from two Wikipedia-based multi-hop QA datasets: HotpotQA and 2WikiMultihopQA. HotpotQA contains 112,779 2-hop questions that are written by native speakers according to two given paragraphs as the context. 2WikiMultihopQA contains 192,606 5-hop questions that are synthesized using manually designed templates to prevent shortcut solutions. We select 124 samples from the two datasets.\n* loogle-MR-mixup and loogle-CR-mixup originate from LooGLE's Long-dependency QA task, specifically the *Multiple information Retrieval* and *Comprehension and Reasoning* subtasks. The *Multiple information Retrieval* task requires aggregation of the evidence that can be directly located in original sentences, while the *Comprehension and Reasoning* task contains implicit evidence within the context, it requires multi-step reasoning to get the correct answers. We select 139 and 99 questions for loogle-MR-mixup and loogle-CR-mixup, respectively.\n* dureader-mixup is built from the DuReader dataset. We first randomly select 200 instances and then manually remove 24 samples whose answers are longer than 360 words.", "### Single-hop QA\n\n\nIn a single-hop QA task, only a single evidence in the context is needed to derive the answer.\n\n\n* loogle-SD-mixup contains 160 unique QA pairs and 800 documents originated from the short-dependency QA task in LooGLE.\n* cmrc-mixup is derived from the CMRC 2018 Public Datasets, designed for Chinese machine reading comprehension. It contains ~20k questions annotated on Wikipedia paragraphs by human experts. We manually pick 200 QA pairs and their corresponding documents as supporting QA pairs and paragraphs.\n* multifieldqa-en-mixup and multifieldqa-zh-mixup are built from the MultiFieldQA datasets in LongBench. We manually remove questions that can be answered using common-sense knowledge without referring to the context, and eventually get 101 and 133 unique QA pairs for multifieldqa-en-mixup and multifieldqa-zh-mixup, respectively.\n* factrecall-en and factrecall-zh are two synthetic datasets designed to assess the LLMs' ability to identify a small piece of evidence (“fact”) located at various locations within a very lengthy context. We write one English fact-question-answer pair for factrecall-en and one Chinese fact-question-answer pair for factrecall-zh. Distracting documents are sourced from *PG-19* dataset (English) and the book of *Dream of the Red Chamber* (Chinese) to create five contexts of different length levels. For each context, we generate 200 documents by inserting the fact at 200 evenly spaced positions within the context.\n\n\nLicense\n=======\n\n\nIn LV-Eval, the cmrc-mixup and lic-mixup datasets follow 'CC-BY-SA-4.0' license, and the other datasets follow 'MIT' license." ]

[ "TAGS\n#language-English #language-Chinese #license-mit #arxiv-2402.05136 #region-us \n", "#### Quick Start\n\n\nOur dataset evaluates the long-text capabilities of the large language models from multiple perspectives. Each subset has different length divisions, so please add a length limit when loading the dataset.", "#### Loading Data\n\n\nIf you want to download the data for hotpotwikiqa\\_mixup, you can visit this link.\nIf you need other subsets of data, simply change the zip file name in the link above.", "#### Data Format\n\n\nAll data in LV-Eval follows the following format. For certain datasets (\"loogle\\_SD\\_mixup,\" \"loogle\\_CR\\_mixup,\" \"loogle\\_MIR\\_mixup\"), there is an additional key called \"answer\\_keywords\". This key indicates the most crucial word or sentence in the answer. During the evaluation of predicted values, if the match between the prediction and the \"answer\\_keywords\" falls below a certain threshold, it directly returns 0. Otherwise, it compares the \"answers\" list with the predicted value.\n\n\nFor some datasets (\"factrecall\\_en,\" \"factrecall\\_zh,\" \"cmrc\\_mixup\"), there is an extra key called \"confusing\\_facts\". This key represents confounding elements added to increase the benchmark difficulty and has been randomly placed within long texts.\n\n\nFor certain datasets (\"hotpotwikiqa\\_mixup,\" \"multifieldqa\\_en\\_mixup,\" \"multifieldqa\\_zh\\_mixup,\" \"lic\\_mixup\"), both \"answer\\_keywords\" and \"confusing\\_facts\" are present.", "#### Evaluation\n\n\nThis repository provides data download for LV-Eval. If you wish to use this dataset for automated evaluation, please refer to our github.\n\n\nTask statistics\n===============\n\n\n\nThe abbreviations for CFI, KPR, AK represent for confusing fact insertion, keyword and phrase replacement, and answer keywords, respectively. The confusing fact insertion has already been inserted into the context and will be displayed in the jsonl file as \"confusing\\_facts\". The answer keywords will be shown in the form of \"answer\\_keywords\" in the jsonl file.\n\n\nTask construction\n=================", "### Multi-hop QA\n\n\nIn a multi-hop QA task, the reasoning process to derive the answer need to gather multiple pieces of information from various locations in the context.\n\n\n* lic-mixup is originated from the Long-instruction-en2zh dataset on Hugging Face. The original Long-instruction-en2zh contains 8,000+ high-quality Chinese multi-doc QA data translated from English. We selected 197 QA pairs and their corresponding documents as supporting data, while the remaining documents serve as distracting data for context mixing.\n* hotpotwikiqa-mixup is originated from two Wikipedia-based multi-hop QA datasets: HotpotQA and 2WikiMultihopQA. HotpotQA contains 112,779 2-hop questions that are written by native speakers according to two given paragraphs as the context. 2WikiMultihopQA contains 192,606 5-hop questions that are synthesized using manually designed templates to prevent shortcut solutions. We select 124 samples from the two datasets.\n* loogle-MR-mixup and loogle-CR-mixup originate from LooGLE's Long-dependency QA task, specifically the *Multiple information Retrieval* and *Comprehension and Reasoning* subtasks. The *Multiple information Retrieval* task requires aggregation of the evidence that can be directly located in original sentences, while the *Comprehension and Reasoning* task contains implicit evidence within the context, it requires multi-step reasoning to get the correct answers. We select 139 and 99 questions for loogle-MR-mixup and loogle-CR-mixup, respectively.\n* dureader-mixup is built from the DuReader dataset. We first randomly select 200 instances and then manually remove 24 samples whose answers are longer than 360 words.", "### Single-hop QA\n\n\nIn a single-hop QA task, only a single evidence in the context is needed to derive the answer.\n\n\n* loogle-SD-mixup contains 160 unique QA pairs and 800 documents originated from the short-dependency QA task in LooGLE.\n* cmrc-mixup is derived from the CMRC 2018 Public Datasets, designed for Chinese machine reading comprehension. It contains ~20k questions annotated on Wikipedia paragraphs by human experts. We manually pick 200 QA pairs and their corresponding documents as supporting QA pairs and paragraphs.\n* multifieldqa-en-mixup and multifieldqa-zh-mixup are built from the MultiFieldQA datasets in LongBench. We manually remove questions that can be answered using common-sense knowledge without referring to the context, and eventually get 101 and 133 unique QA pairs for multifieldqa-en-mixup and multifieldqa-zh-mixup, respectively.\n* factrecall-en and factrecall-zh are two synthetic datasets designed to assess the LLMs' ability to identify a small piece of evidence (“fact”) located at various locations within a very lengthy context. We write one English fact-question-answer pair for factrecall-en and one Chinese fact-question-answer pair for factrecall-zh. Distracting documents are sourced from *PG-19* dataset (English) and the book of *Dream of the Red Chamber* (Chinese) to create five contexts of different length levels. For each context, we generate 200 documents by inserting the fact at 200 evenly spaced positions within the context.\n\n\nLicense\n=======\n\n\nIn LV-Eval, the cmrc-mixup and lic-mixup datasets follow 'CC-BY-SA-4.0' license, and the other datasets follow 'MIT' license." ]

[ "task_categories:text-generation", "language_creators:crowdsourced", "language_creators:expert-generated", "language_creators:machine-generated", "multilinguality:multilingual", "size_categories:10K<n<100K", "source_datasets:original", "source_datasets:extended", "language:afr", "language:sqi", "language:amh", "language:ara", "language:aze", "language:bel", "language:ben", "language:bul", "language:cat", "language:ceb", "language:ces", "language:kur", "language:cym", "language:dan", "language:deu", "language:ell", "language:eng", "language:epo", "language:est", "language:eus", "language:fin", "language:fra", "language:gla", "language:gle", "language:glg", "language:guj", "language:hat", "language:hau", "language:heb", "language:hin", "language:hun", "language:hye", "language:ibo", "language:ind", "language:isl", "language:ita", "language:jav", "language:jpn", "language:kan", "language:kat", "language:kaz", "language:mon", "language:khm", "language:kir", "language:kor", "language:lao", "language:lit", "language:ltz", "language:lav", "language:mal", "language:mar", "language:mkd", "language:mlt", "language:mri", "language:mya", "language:nld", "language:nor", "language:nep", "language:sot", "language:pus", "language:pes", "language:mlg", "language:pol", "language:por", "language:ron", "language:rus", "language:sin", "language:slk", "language:slv", "language:smo", "language:sna", "language:snd", "language:som", "language:spa", "language:srp", "language:sun", "language:swe", "language:swa", "language:tam", "language:tel", "language:tgk", "language:tha", "language:tur", "language:ukr", "language:urd", "language:uzb", "language:vie", "language:xho", "language:yid", "language:yor", "language:zho", "language:msa", "language:zul", "language:ace", "language:bjn", "language:kas", "language:kau", "language:min", "language:mni", "language:taq", "language:nso", "license:apache-2.0", "arxiv:2402.06619", "region:us" ]

[ "2402.06619" ]

[ "afr", "sqi", "amh", "ara", "aze", "bel", "ben", "bul", "cat", "ceb", "ces", "kur", "cym", "dan", "deu", "ell", "eng", "epo", "est", "eus", "fin", "fra", "gla", "gle", "glg", "guj", "hat", "hau", "heb", "hin", "hun", "hye", "ibo", "ind", "isl", "ita", "jav", "jpn", "kan", "kat", "kaz", "mon", "khm", "kir", "kor", "lao", "lit", "ltz", "lav", "mal", "mar", "mkd", "mlt", "mri", "mya", "nld", "nor", "nep", "sot", "pus", "pes", "mlg", "pol", "por", "ron", "rus", "sin", "slk", "slv", "smo", "sna", "snd", "som", "spa", "srp", "sun", "swe", "swa", "tam", "tel", "tgk", "tha", "tur", "ukr", "urd", "uzb", "vie", "xho", "yid", "yor", "zho", "msa", "zul", "ace", "bjn", "kas", "kau", "min", "mni", "taq", "nso" ]

[ "### Languages\n\n\n\n **aya-human-annotated** \nISO Code: 'tel', Language: Telugu, Resources: Low\nISO Code: 'yor', Language: Yorùbá, Resources: Low\nISO Code: 'arb', Language: Arabic, Resources: High\nISO Code: 'tur', Language: Turkish, Resources: High\nISO Code: 'por', Language: Portuguese, Resources: High\nISO Code: 'zho', Language: Chinese (Simplified), Resources: High\nISO Code: 'eng', Language: English, Resources: High\n\n\n\n\n **dolly-machine-translated** \nISO Code: 'ace', Language: Achinese, Resources: Low\nISO Code: 'afr', Language: Afrikaans, Resources: Mid\nISO Code: 'amh', Language: Amharic, Resources: Low\nISO Code: 'ara' ('arb', 'acm', 'acq', 'aeb', 'ajp', 'apc', 'ars', 'ary' & 'arz'), Language: Arabic (Standard, Gelet Iraqi, Ta'izzi-Adeni, Tunisian, South Levantine, North Levantine, Najdi, Moroccan & Egyptian), Resources: High\nISO Code: 'aze' ('azb' & 'azj'), Language: Azerbaijani (South & North), Resources: Low\nISO Code: 'bel', Language: Belarusian, Resources: Mid\nISO Code: 'ben', Language: Bengali, Resources: Mid\nISO Code: 'bjn', Language: Banjar, Resources: Low\nISO Code: 'bul', Language: Bulgarian, Resources: Mid\nISO Code: 'cat', Language: Catalan, Resources: High\nISO Code: 'ceb', Language: Cebuano, Resources: Mid\nISO Code: 'ces', Language: Czech, Resources: High\nISO Code: 'cym', Language: Welsh, Resources: Low\nISO Code: 'dan', Language: Danish, Resources: Mid\nISO Code: 'deu', Language: German, Resources: High\nISO Code: 'ell', Language: Greek, Resources: Mid\nISO Code: 'eng', Language: English, Resources: High\nISO Code: 'epo', Language: Esperanto, Resources: Low\nISO Code: 'est', Language: Estonian, Resources: Mid\nISO Code: 'eus', Language: Basque, Resources: High\nISO Code: 'fin', Language: Finnish, Resources: High\nISO Code: 'fra', Language: French, Resources: High\nISO Code: 'gla', Language: Scottish Gaelic, Resources: Low\nISO Code: 'gle', Language: Irish, Resources: Low\nISO Code: 'glg', Language: Galician, Resources: Mid\nISO Code: 'guj', Language: Gujarati, Resources: Low\nISO Code: 'hat', Language: Haitian Creole, Resources: Low\nISO Code: 'hau', Language: Hausa, Resources: Low\nISO Code: 'heb', Language: Hebrew, Resources: Mid\nISO Code: 'hin', Language: Hindi, Resources: High\nISO Code: 'hun', Language: Hungarian, Resources: High\nISO Code: 'hye', Language: Armenian, Resources: Low\nISO Code: 'ibo', Language: Igbo, Resources: Low\nISO Code: 'ind', Language: Indonesian, Resources: Mid\nISO Code: 'isl', Language: Icelandic, Resources: Low\nISO Code: 'ita', Language: Italian, Resources: High\nISO Code: 'jav', Language: Javanese, Resources: Low\nISO Code: 'jpn', Language: Japanese, Resources: High\nISO Code: 'kan', Language: Kannada, Resources: Low\nISO Code: 'kas', Language: Kashmiri, Resources: Low\nISO Code: 'kat', Language: Georgian, Resources: Mid\nISO Code: 'kau' ('knc'), Language: Kanuri (Central), Resources: Low\nISO Code: 'kaz', Language: Kazakh, Resources: Mid\nISO Code: 'khm', Language: Khmer, Resources: Low\nISO Code: 'kir', Language: Kyrgyz, Resources: Low\nISO Code: 'kor', Language: Korean, Resources: High\nISO Code: 'kur' ('ckb' & 'kmr'), Language: Kurdish (Central & Northern), Resources: Low\nISO Code: 'lao', Language: Lao, Resources: Low\nISO Code: 'lav' ('lvs'), Language: Latvian (Standard), Resources: Mid\nISO Code: 'lit', Language: Lithuanian, Resources: Mid\nISO Code: 'ltz', Language: Luxembourgish, Resources: Low\nISO Code: 'mal', Language: Malayalam, Resources: Low\nISO Code: 'mar', Language: Marathi, Resources: Low\nISO Code: 'min', Language: Minangkabau, Resources: Low\nISO Code: 'mkd', Language: Macedonian, Resources: Low\nISO Code: 'mlg' ('plt'), Language: Malagasy (Plateau), Resources: Low\nISO Code: 'mlt', Language: Maltese, Resources: Low\nISO Code: 'mni', Language: Manipuri, Resources: Low\nISO Code: 'mon' ('khk'), Language: Mongolian (Khalkha), Resources: Low\nISO Code: 'mri', Language: Maori, Resources: Low\nISO Code: 'msa' ('zsm'), Language: Malay (Standard), Resources: Mid\nISO Code: 'mya', Language: Burmese, Resources: Low\nISO Code: 'nep' ('npi'), Language: Nepali, Resources: Low\nISO Code: 'nld', Language: Dutch, Resources: High\nISO Code: 'nor' ('nno' & 'nob'), Language: Norwegian (Nynorsk & Bokmål), Resources: Low\nISO Code: 'nso', Language: Northern Sotho, Resources: Low\nISO Code: 'pes', Language: Persian, Resources: High\nISO Code: 'pol', Language: Polish, Resources: High\nISO Code: 'por', Language: Portuguese, Resources: High\nISO Code: 'pus' ('pbt'), Language: Pashto (Southern), Resources: Low\nISO Code: 'ron', Language: Romanian, Resources: Mid\nISO Code: 'rus', Language: Russian, Resources: High\nISO Code: 'sin', Language: Sinhala, Resources: Low\nISO Code: 'slk', Language: Slovak, Resources: Mid\nISO Code: 'slv', Language: Slovenian, Resources: Mid\nISO Code: 'smo', Language: Samoan, Resources: Low\nISO Code: 'sna', Language: Shona, Resources: Low\nISO Code: 'snd', Language: Sindhi, Resources: Low\nISO Code: 'som', Language: Somali, Resources: Low\nISO Code: 'sot', Language: Southern Sotho, Resources: Low\nISO Code: 'spa', Language: Spanish, Resources: High\nISO Code: 'sqi' ('als'), Language: Albanian (Tosk), Resources: Low\nISO Code: 'srp', Language: Serbian, Resources: High\nISO Code: 'sun', Language: Sundanese, Resources: Low\nISO Code: 'swa' ('swh'), Language: Swahili (Coastal), Resources: Low\nISO Code: 'swe', Language: Swedish, Resources: High\nISO Code: 'tam', Language: Tamil, Resources: Mid\nISO Code: 'taq', Language: Tamasheq, Resources: Low\nISO Code: 'tel', Language: Telugu, Resources: Low\nISO Code: 'tgk', Language: Tajik, Resources: Low\nISO Code: 'tha', Language: Thai, Resources: Mid\nISO Code: 'tur', Language: Turkish, Resources: High\nISO Code: 'ukr', Language: Ukrainian, Resources: Mid\nISO Code: 'urd', Language: Urdu, Resources: Mid\nISO Code: 'uzb' ('uzn'), Language: Uzbek (Nothern), Resources: Mid\nISO Code: 'vie', Language: Vietnamese, Resources: High\nISO Code: 'xho', Language: Xhosa, Resources: Low\nISO Code: 'yid' ('ydd'), Language: Yiddish (Eastern), Resources: Low\nISO Code: 'yor', Language: Yoruba, Resources: Low\nISO Code: 'zho' (+ 'yue'), Language: Chinese (Simplified & Cantonese), Resources: High\nISO Code: 'zul', Language: Zulu, Resources: Low\n\n\n\n\n **dolly-human-edited** \nISO Code: 'arb', Language: Arabic, Resources: High\nISO Code: 'fra', Language: French, Resources: High\nISO Code: 'hin', Language: Hindi, Resources: High\nISO Code: 'rus', Language: Russian, Resources: High\nISO Code: 'spa', Language: Spanish, Resources: High\nISO Code: 'srp', Language: Serbian, Resources: High\n\n\n\n \n\nMotivations & Intentions\n========================\n\n\n* Curation Rationale: This evaluation suite is tailored to test the generation quality of multilingual models, with the aim of balancing language coverage and human-sourced quality.\nIt covers prompts originally written in each language, as well as English-centric translated, and manually curated or edited prompts for a linguistically broad, but rich testbed.\nThe list of languages was initially established from mT5 and aligned with the annotators’ language list and the NLLB translation model.\n\n\nKnown Limitations\n=================\n\n\n* Translation Quality: Note that the expressiveness of the 'dolly-machine-translated' subset is limited by the quality of the translation model and may adversely impact an estimate of ability in languages where translations are not adequate. If this subset is used for testing, we recommend it be paired and reported with the professionally post-edited 'dolly-human-edited' subset or the 'aya-human-annotated' set, which, while covering only 7 languages, is entirely created by proficient target language speakers.\n\n\n\n\n---\n\n\nAdditional Information\n======================\n\n\nProvenance\n----------\n\n\n* Methods Used: combination of original annotations by volunteers, automatic translation, and post-editing of translations by professional annotators.\n* Methodology Details:\n\t+ *Source:* Original annotations from Aya dataset along with translations and post-edits of Dolly dataset\n\t+ *Platform:* Aya Annotation Platform\n\t+ *Dates of Collection:* May 2023 - Dec 2023\n\n\nDataset Version and Maintenance\n-------------------------------\n\n\n* Maintenance Status: Actively Maintained\n* Version Details:\n\t+ *Current version:* 1.0\n\t+ *Last Update:* 02/2024\n\t+ *First Release:* 02/2024\n* Maintenance Plan: No updates planned.\n\n\nAuthorship\n----------\n\n\n* Publishing Organization: Cohere For AI\n* Industry Type: Not-for-profit - Tech\n* Contact Details: URL\n\n\nLicensing Information\n---------------------\n\n\nThis dataset can be used for any purpose, whether academic or commercial, under the terms of the Apache 2.0 License." ]

[ "TAGS\n#task_categories-text-generation #language_creators-crowdsourced #language_creators-expert-generated #language_creators-machine-generated #multilinguality-multilingual #size_categories-10K<n<100K #source_datasets-original #source_datasets-extended #language-Afrikaans #language-Albanian #language-Amharic #language-Arabic #language-Azerbaijani #language-Belarusian #language-Bengali #language-Bulgarian #language-Catalan #language-Cebuano #language-Czech #language-Kurdish #language-Welsh #language-Danish #language-German #language-Modern Greek (1453-) #language-English #language-Esperanto #language-Estonian #language-Basque #language-Finnish #language-French #language-Scottish Gaelic #language-Irish #language-Galician #language-Gujarati #language-Haitian #language-Hausa #language-Hebrew #language-Hindi #language-Hungarian #language-Armenian #language-Igbo #language-Indonesian #language-Icelandic #language-Italian #language-Javanese #language-Japanese #language-Kannada #language-Georgian #language-Kazakh #language-Mongolian #language-Khmer #language-Kirghiz #language-Korean #language-Lao #language-Lithuanian #language-Luxembourgish #language-Latvian #language-Malayalam #language-Marathi #language-Macedonian #language-Maltese #language-Maori #language-Burmese #language-Dutch #language-Norwegian #language-Nepali (macrolanguage) #language-Southern Sotho #language-Pushto #language-Iranian Persian #language-Malagasy #language-Polish #language-Portuguese #language-Romanian #language-Russian #language-Sinhala #language-Slovak #language-Slovenian #language-Samoan #language-Shona #language-Sindhi #language-Somali #language-Spanish #language-Serbian #language-Sundanese #language-Swedish #language-Swahili (macrolanguage) #language-Tamil #language-Telugu #language-Tajik #language-Thai #language-Turkish #language-Ukrainian #language-Urdu #language-Uzbek #language-Vietnamese #language-Xhosa #language-Yiddish #language-Yoruba #language-Chinese #language-Malay (macrolanguage) #language-Zulu #language-Achinese #language-Banjar #language-Kashmiri #language-Kanuri #language-Minangkabau #language-Manipuri #language-Tamasheq #language-Pedi #license-apache-2.0 #arxiv-2402.06619 #region-us \n", "### Languages\n\n\n\n **aya-human-annotated** \nISO Code: 'tel', Language: Telugu, Resources: Low\nISO Code: 'yor', Language: Yorùbá, Resources: Low\nISO Code: 'arb', Language: Arabic, Resources: High\nISO Code: 'tur', Language: Turkish, Resources: High\nISO Code: 'por', Language: Portuguese, Resources: High\nISO Code: 'zho', Language: Chinese (Simplified), Resources: High\nISO Code: 'eng', Language: English, Resources: High\n\n\n\n\n **dolly-machine-translated** \nISO Code: 'ace', Language: Achinese, Resources: Low\nISO Code: 'afr', Language: Afrikaans, Resources: Mid\nISO Code: 'amh', Language: Amharic, Resources: Low\nISO Code: 'ara' ('arb', 'acm', 'acq', 'aeb', 'ajp', 'apc', 'ars', 'ary' & 'arz'), Language: Arabic (Standard, Gelet Iraqi, Ta'izzi-Adeni, Tunisian, South Levantine, North Levantine, Najdi, Moroccan & Egyptian), Resources: High\nISO Code: 'aze' ('azb' & 'azj'), Language: Azerbaijani (South & North), Resources: Low\nISO Code: 'bel', Language: Belarusian, Resources: Mid\nISO Code: 'ben', Language: Bengali, Resources: Mid\nISO Code: 'bjn', Language: Banjar, Resources: Low\nISO Code: 'bul', Language: Bulgarian, Resources: Mid\nISO Code: 'cat', Language: Catalan, Resources: High\nISO Code: 'ceb', Language: Cebuano, Resources: Mid\nISO Code: 'ces', Language: Czech, Resources: High\nISO Code: 'cym', Language: Welsh, Resources: Low\nISO Code: 'dan', Language: Danish, Resources: Mid\nISO Code: 'deu', Language: German, Resources: High\nISO Code: 'ell', Language: Greek, Resources: Mid\nISO Code: 'eng', Language: English, Resources: High\nISO Code: 'epo', Language: Esperanto, Resources: Low\nISO Code: 'est', Language: Estonian, Resources: Mid\nISO Code: 'eus', Language: Basque, Resources: High\nISO Code: 'fin', Language: Finnish, Resources: High\nISO Code: 'fra', Language: French, Resources: High\nISO Code: 'gla', Language: Scottish Gaelic, Resources: Low\nISO Code: 'gle', Language: Irish, Resources: Low\nISO Code: 'glg', Language: Galician, Resources: Mid\nISO Code: 'guj', Language: Gujarati, Resources: Low\nISO Code: 'hat', Language: Haitian Creole, Resources: Low\nISO Code: 'hau', Language: Hausa, Resources: Low\nISO Code: 'heb', Language: Hebrew, Resources: Mid\nISO Code: 'hin', Language: Hindi, Resources: High\nISO Code: 'hun', Language: Hungarian, Resources: High\nISO Code: 'hye', Language: Armenian, Resources: Low\nISO Code: 'ibo', Language: Igbo, Resources: Low\nISO Code: 'ind', Language: Indonesian, Resources: Mid\nISO Code: 'isl', Language: Icelandic, Resources: Low\nISO Code: 'ita', Language: Italian, Resources: High\nISO Code: 'jav', Language: Javanese, Resources: Low\nISO Code: 'jpn', Language: Japanese, Resources: High\nISO Code: 'kan', Language: Kannada, Resources: Low\nISO Code: 'kas', Language: Kashmiri, Resources: Low\nISO Code: 'kat', Language: Georgian, Resources: Mid\nISO Code: 'kau' ('knc'), Language: Kanuri (Central), Resources: Low\nISO Code: 'kaz', Language: Kazakh, Resources: Mid\nISO Code: 'khm', Language: Khmer, Resources: Low\nISO Code: 'kir', Language: Kyrgyz, Resources: Low\nISO Code: 'kor', Language: Korean, Resources: High\nISO Code: 'kur' ('ckb' & 'kmr'), Language: Kurdish (Central & Northern), Resources: Low\nISO Code: 'lao', Language: Lao, Resources: Low\nISO Code: 'lav' ('lvs'), Language: Latvian (Standard), Resources: Mid\nISO Code: 'lit', Language: Lithuanian, Resources: Mid\nISO Code: 'ltz', Language: Luxembourgish, Resources: Low\nISO Code: 'mal', Language: Malayalam, Resources: Low\nISO Code: 'mar', Language: Marathi, Resources: Low\nISO Code: 'min', Language: Minangkabau, Resources: Low\nISO Code: 'mkd', Language: Macedonian, Resources: Low\nISO Code: 'mlg' ('plt'), Language: Malagasy (Plateau), Resources: Low\nISO Code: 'mlt', Language: Maltese, Resources: Low\nISO Code: 'mni', Language: Manipuri, Resources: Low\nISO Code: 'mon' ('khk'), Language: Mongolian (Khalkha), Resources: Low\nISO Code: 'mri', Language: Maori, Resources: Low\nISO Code: 'msa' ('zsm'), Language: Malay (Standard), Resources: Mid\nISO Code: 'mya', Language: Burmese, Resources: Low\nISO Code: 'nep' ('npi'), Language: Nepali, Resources: Low\nISO Code: 'nld', Language: Dutch, Resources: High\nISO Code: 'nor' ('nno' & 'nob'), Language: Norwegian (Nynorsk & Bokmål), Resources: Low\nISO Code: 'nso', Language: Northern Sotho, Resources: Low\nISO Code: 'pes', Language: Persian, Resources: High\nISO Code: 'pol', Language: Polish, Resources: High\nISO Code: 'por', Language: Portuguese, Resources: High\nISO Code: 'pus' ('pbt'), Language: Pashto (Southern), Resources: Low\nISO Code: 'ron', Language: Romanian, Resources: Mid\nISO Code: 'rus', Language: Russian, Resources: High\nISO Code: 'sin', Language: Sinhala, Resources: Low\nISO Code: 'slk', Language: Slovak, Resources: Mid\nISO Code: 'slv', Language: Slovenian, Resources: Mid\nISO Code: 'smo', Language: Samoan, Resources: Low\nISO Code: 'sna', Language: Shona, Resources: Low\nISO Code: 'snd', Language: Sindhi, Resources: Low\nISO Code: 'som', Language: Somali, Resources: Low\nISO Code: 'sot', Language: Southern Sotho, Resources: Low\nISO Code: 'spa', Language: Spanish, Resources: High\nISO Code: 'sqi' ('als'), Language: Albanian (Tosk), Resources: Low\nISO Code: 'srp', Language: Serbian, Resources: High\nISO Code: 'sun', Language: Sundanese, Resources: Low\nISO Code: 'swa' ('swh'), Language: Swahili (Coastal), Resources: Low\nISO Code: 'swe', Language: Swedish, Resources: High\nISO Code: 'tam', Language: Tamil, Resources: Mid\nISO Code: 'taq', Language: Tamasheq, Resources: Low\nISO Code: 'tel', Language: Telugu, Resources: Low\nISO Code: 'tgk', Language: Tajik, Resources: Low\nISO Code: 'tha', Language: Thai, Resources: Mid\nISO Code: 'tur', Language: Turkish, Resources: High\nISO Code: 'ukr', Language: Ukrainian, Resources: Mid\nISO Code: 'urd', Language: Urdu, Resources: Mid\nISO Code: 'uzb' ('uzn'), Language: Uzbek (Nothern), Resources: Mid\nISO Code: 'vie', Language: Vietnamese, Resources: High\nISO Code: 'xho', Language: Xhosa, Resources: Low\nISO Code: 'yid' ('ydd'), Language: Yiddish (Eastern), Resources: Low\nISO Code: 'yor', Language: Yoruba, Resources: Low\nISO Code: 'zho' (+ 'yue'), Language: Chinese (Simplified & Cantonese), Resources: High\nISO Code: 'zul', Language: Zulu, Resources: Low\n\n\n\n\n **dolly-human-edited** \nISO Code: 'arb', Language: Arabic, Resources: High\nISO Code: 'fra', Language: French, Resources: High\nISO Code: 'hin', Language: Hindi, Resources: High\nISO Code: 'rus', Language: Russian, Resources: High\nISO Code: 'spa', Language: Spanish, Resources: High\nISO Code: 'srp', Language: Serbian, Resources: High\n\n\n\n \n\nMotivations & Intentions\n========================\n\n\n* Curation Rationale: This evaluation suite is tailored to test the generation quality of multilingual models, with the aim of balancing language coverage and human-sourced quality.\nIt covers prompts originally written in each language, as well as English-centric translated, and manually curated or edited prompts for a linguistically broad, but rich testbed.\nThe list of languages was initially established from mT5 and aligned with the annotators’ language list and the NLLB translation model.\n\n\nKnown Limitations\n=================\n\n\n* Translation Quality: Note that the expressiveness of the 'dolly-machine-translated' subset is limited by the quality of the translation model and may adversely impact an estimate of ability in languages where translations are not adequate. If this subset is used for testing, we recommend it be paired and reported with the professionally post-edited 'dolly-human-edited' subset or the 'aya-human-annotated' set, which, while covering only 7 languages, is entirely created by proficient target language speakers.\n\n\n\n\n---\n\n\nAdditional Information\n======================\n\n\nProvenance\n----------\n\n\n* Methods Used: combination of original annotations by volunteers, automatic translation, and post-editing of translations by professional annotators.\n* Methodology Details:\n\t+ *Source:* Original annotations from Aya dataset along with translations and post-edits of Dolly dataset\n\t+ *Platform:* Aya Annotation Platform\n\t+ *Dates of Collection:* May 2023 - Dec 2023\n\n\nDataset Version and Maintenance\n-------------------------------\n\n\n* Maintenance Status: Actively Maintained\n* Version Details:\n\t+ *Current version:* 1.0\n\t+ *Last Update:* 02/2024\n\t+ *First Release:* 02/2024\n* Maintenance Plan: No updates planned.\n\n\nAuthorship\n----------\n\n\n* Publishing Organization: Cohere For AI\n* Industry Type: Not-for-profit - Tech\n* Contact Details: URL\n\n\nLicensing Information\n---------------------\n\n\nThis dataset can be used for any purpose, whether academic or commercial, under the terms of the Apache 2.0 License." ]

[ "region:us" ]

[]

[]

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

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

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"NLLB3.3B_XQuAD_TH_sent_span\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"NLLB3.3B_XQuAD_TH_sent_span\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_hotpot_train5000_eval5000_v1_ic_qa\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_hotpot_train5000_eval5000_v1_ic_qa\"\n\nMore Information needed" ]

[ "size_categories:n<1K", "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 'text'.\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+ sentiment is of type 'label\\_selection' with the following allowed values ['positive', 'neutral', 'negative'].\n\t+ mixed-emotion is of type 'multi\\_label\\_selection' with the following allowed values ['joy', 'anger', 'sadness', 'fear', 'surprise', 'love'].\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) sentiment-suggestion is of type 'label\\_selection' with the following allowed values ['positive', 'neutral', 'negative'].\n\t+ (optional) mixed-emotion-suggestion is of type 'multi\\_label\\_selection' with the following allowed values ['joy', 'anger', 'sadness', 'fear', 'surprise', 'love'].\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\nEmotion is a dataset of English Twitter messages with six basic emotions: anger, fear, joy, love, sadness, and surprise.", "#### 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-n<1K #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 'text'.\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+ sentiment is of type 'label\\_selection' with the following allowed values ['positive', 'neutral', 'negative'].\n\t+ mixed-emotion is of type 'multi\\_label\\_selection' with the following allowed values ['joy', 'anger', 'sadness', 'fear', 'surprise', 'love'].\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) sentiment-suggestion is of type 'label\\_selection' with the following allowed values ['positive', 'neutral', 'negative'].\n\t+ (optional) mixed-emotion-suggestion is of type 'multi\\_label\\_selection' with the following allowed values ['joy', 'anger', 'sadness', 'fear', 'surprise', 'love'].\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\nEmotion is a dataset of English Twitter messages with six basic emotions: anger, fear, joy, love, sadness, and surprise.", "#### 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 Croatian Parliamentary Spoken Dataset ParlaSpeech-HR 2.0\n\nURL\n\nThe ParlaSpeech-HR dataset is built from the transcripts of parliamentary proceedings available in the Croatian part of the ParlaMint corpus, and the parliamentary recordings available from the Croatian Parliament's YouTube channel.\n\nThe corpus consists of audio segments that correspond to specific sentences in the transcripts. The transcript contains word-level alignments to the recordings, each instance consisting of character and millisecond start and end offsets, allowing for simple further segmentation of long sentences into shorter segments for ASR and other memory-sensitive applications. Sequences longer than 30 seconds have already been removed from this dataset, which should allow for a simple usage on most modern GPUs.\n\nEach segment has an identifier reference to the ParlaMint 4.0 corpus (URL via the utterance ID and character offsets.\n\nWhile in the original dataset all the speaker information from the ParlaMint corpus is available via the 'speaker_info' attribute, in the HuggingFace version only a subset of metadata is available, namely: the date, the name of the speaker, their gender, year of birth, party affiliation at that point in time, status of the party at that point in time (coalition or opposition), and party orientation (left, right, centre etc.).\n\nDifferent to the original dataset, this version has also a 'text_normalised' attribute, which contains the text with parliamentary comments ('[[Applause]]' and similar) removed.\n\nIf you use the dataset, please cite the following paper:" ]

[ "TAGS\n#region-us \n", "# The Croatian Parliamentary Spoken Dataset ParlaSpeech-HR 2.0\n\nURL\n\nThe ParlaSpeech-HR dataset is built from the transcripts of parliamentary proceedings available in the Croatian part of the ParlaMint corpus, and the parliamentary recordings available from the Croatian Parliament's YouTube channel.\n\nThe corpus consists of audio segments that correspond to specific sentences in the transcripts. The transcript contains word-level alignments to the recordings, each instance consisting of character and millisecond start and end offsets, allowing for simple further segmentation of long sentences into shorter segments for ASR and other memory-sensitive applications. Sequences longer than 30 seconds have already been removed from this dataset, which should allow for a simple usage on most modern GPUs.\n\nEach segment has an identifier reference to the ParlaMint 4.0 corpus (URL via the utterance ID and character offsets.\n\nWhile in the original dataset all the speaker information from the ParlaMint corpus is available via the 'speaker_info' attribute, in the HuggingFace version only a subset of metadata is available, namely: the date, the name of the speaker, their gender, year of birth, party affiliation at that point in time, status of the party at that point in time (coalition or opposition), and party orientation (left, right, centre etc.).\n\nDifferent to the original dataset, this version has also a 'text_normalised' attribute, which contains the text with parliamentary comments ('[[Applause]]' and similar) removed.\n\nIf you use the dataset, please cite the following paper:" ]

[ "region:us" ]

[]

[]

[ "# The Polish Parliamentary Spoken Dataset ParlaSpeech-PL 1.0\n\nURL\n\nThe ParlaSpeech-PL dataset is built from the transcripts of parliamentary proceedings available in the Polish part of the ParlaMint corpus, and the parliamentary recordings available from the Polish Parliament's YouTube channel.\n\nThe corpus consists of audio segments that correspond to specific sentences in the transcripts. The transcript contains word-level alignments to the recordings, each instance consisting of character and millisecond start and end offsets, allowing for simple further segmentation of long sentences into shorter segments for ASR and other memory-sensitive applications. Sequences longer than 30 seconds have already been removed from this dataset, which should allow for a simple usage on most modern GPUs.\n\nEach segment has an identifier reference to the ParlaMint 4.0 corpus (URL via the utterance ID and character offsets.\n\nWhile in the original dataset all the speaker information from the ParlaMint corpus is available via the 'speaker_info' attribute, in the HuggingFace version only a subset of metadata is available, namely: the date, the name of the speaker, their gender, year of birth, party affiliation at that point in time, status of the party at that point in time (coalition or opposition), and party orientation (left, right, centre etc.).\n\nDifferent to the original dataset, this version has also a 'text_normalised' attribute, which contains the text with parliamentary comments ('[[Applause]]' and similar) removed.\n\nIf you use the dataset, please cite the following paper:" ]

[ "TAGS\n#region-us \n", "# The Polish Parliamentary Spoken Dataset ParlaSpeech-PL 1.0\n\nURL\n\nThe ParlaSpeech-PL dataset is built from the transcripts of parliamentary proceedings available in the Polish part of the ParlaMint corpus, and the parliamentary recordings available from the Polish Parliament's YouTube channel.\n\nThe corpus consists of audio segments that correspond to specific sentences in the transcripts. The transcript contains word-level alignments to the recordings, each instance consisting of character and millisecond start and end offsets, allowing for simple further segmentation of long sentences into shorter segments for ASR and other memory-sensitive applications. Sequences longer than 30 seconds have already been removed from this dataset, which should allow for a simple usage on most modern GPUs.\n\nEach segment has an identifier reference to the ParlaMint 4.0 corpus (URL via the utterance ID and character offsets.\n\nWhile in the original dataset all the speaker information from the ParlaMint corpus is available via the 'speaker_info' attribute, in the HuggingFace version only a subset of metadata is available, namely: the date, the name of the speaker, their gender, year of birth, party affiliation at that point in time, status of the party at that point in time (coalition or opposition), and party orientation (left, right, centre etc.).\n\nDifferent to the original dataset, this version has also a 'text_normalised' attribute, which contains the text with parliamentary comments ('[[Applause]]' and similar) removed.\n\nIf you use the dataset, please cite the following paper:" ]

[ "region:us" ]

[]

[]

[]

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

[ "size_categories:1K<n<10K", "language:yue", "license:cc-by-nc-4.0", "sft", "alpaca", "region:us" ]

[]

[ "yue" ]

[ "## Dataset Card for Cantonese Alpaca\n\n!Cantonese Alpaca\n\n- repository: (URL", "## Dataset Description\n\nThis dataset contains Cantonese Instruction-Following generated by Gemini Pro using Stanford's Alpaca prompts for fine-tuning LLMs.\n\nAttention: This dataset is generated by Gemini Pro and has not undergone rigorous verification. The content may contain errors. Please keep this in mind when using it.", "## Licensing Information\n\nThe dataset is available under the Creative Commons NonCommercial (CC BY-NC 4.0)." ]

[ "TAGS\n#size_categories-1K<n<10K #language-Yue Chinese #license-cc-by-nc-4.0 #sft #alpaca #region-us \n", "## Dataset Card for Cantonese Alpaca\n\n!Cantonese Alpaca\n\n- repository: (URL", "## Dataset Description\n\nThis dataset contains Cantonese Instruction-Following generated by Gemini Pro using Stanford's Alpaca prompts for fine-tuning LLMs.\n\nAttention: This dataset is generated by Gemini Pro and has not undergone rigorous verification. The content may contain errors. Please keep this in mind when using it.", "## Licensing Information\n\nThe dataset is available under the Creative Commons NonCommercial (CC BY-NC 4.0)." ]

[ "size_categories:n<1K", "license:gpl-3.0", "art", "region:us" ]

[]

[]

[]

[ "TAGS\n#size_categories-n<1K #license-gpl-3.0 #art #region-us \n" ]

[ "task_categories:text-classification", "language:code", "language:en", "license:other", "code", "commit_message_generation", "region:us" ]

[]

[ "code", "en" ]

[]

[ "TAGS\n#task_categories-text-classification #language-code #language-English #license-other #code #commit_message_generation #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# 한국어 위키피디아 형태소 분석 데이터셋\n\n- 한국어 형태소분석 관련 테스트를 위한 더미 데이터입니다.\n- 위키피디아 한국어 텍스트를 Mecab으로 분석하여 제작하였습니다.\n- 위키피디아 데이터 출처 : URL\n- 한국어 Mecab 다운로드 페이지 : URL", "## License\nCC-BY-SA 3.0 which kowiki dump dataset is licensed" ]

[ "TAGS\n#region-us \n", "# 한국어 위키피디아 형태소 분석 데이터셋\n\n- 한국어 형태소분석 관련 테스트를 위한 더미 데이터입니다.\n- 위키피디아 한국어 텍스트를 Mecab으로 분석하여 제작하였습니다.\n- 위키피디아 데이터 출처 : URL\n- 한국어 Mecab 다운로드 페이지 : URL", "## License\nCC-BY-SA 3.0 which kowiki dump dataset is licensed" ]

[ "size_categories:10K<n<100K", "language:es", "license:apache-2.0", "hate speech", "insults", "spanish", "offensive expressions", "offensive language", "region:us" ]

[]

[ "es" ]

[ "### Dataset Description\n\nPaper: SHARE: A Lexicon of Harmful Expressions by Spanish Speakers\n\nPoint of Contact: URL@URL, maite@URL", "### Source Data\n\nTelegram", "### Licensing Information\n\nSHARE is released under the Apache-2.0 License. \n\n\n'''bibtex\n@inproceedings{plaza-del-arco-etal-2022-share,\n title = \"{SHARE}: A Lexicon of Harmful Expressions by {S}panish Speakers\",\n author = \"{Plaza-del-Arco}, Flor Miriam and\n Parras Portillo, Ana Belén and\n López-Úbeda, Pilar and\n Gil, Beatriz and\n Martín-Valdivia, María-Teresa\",\n booktitle = \"Proceedings of the Thirteenth Language Resources and Evaluation Conference\",\n month = jun,\n year = \"2022\",\n address = \"Marseille, France\",\n publisher = \"European Language Resources Association\",\n url = \"URL\n pages = \"1307--1316\"}" ]

[ "TAGS\n#size_categories-10K<n<100K #language-Spanish #license-apache-2.0 #hate speech #insults #spanish #offensive expressions #offensive language #region-us \n", "### Dataset Description\n\nPaper: SHARE: A Lexicon of Harmful Expressions by Spanish Speakers\n\nPoint of Contact: URL@URL, maite@URL", "### Source Data\n\nTelegram", "### Licensing Information\n\nSHARE is released under the Apache-2.0 License. \n\n\n'''bibtex\n@inproceedings{plaza-del-arco-etal-2022-share,\n title = \"{SHARE}: A Lexicon of Harmful Expressions by {S}panish Speakers\",\n author = \"{Plaza-del-Arco}, Flor Miriam and\n Parras Portillo, Ana Belén and\n López-Úbeda, Pilar and\n Gil, Beatriz and\n Martín-Valdivia, María-Teresa\",\n booktitle = \"Proceedings of the Thirteenth Language Resources and Evaluation Conference\",\n month = jun,\n year = \"2022\",\n address = \"Marseille, France\",\n publisher = \"European Language Resources Association\",\n url = \"URL\n pages = \"1307--1316\"}" ]

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

[]

[ "en" ]

[ "# Whatscooking.restaurants", "## Overview\n\nThis dataset provides detailed information about various restaurants, including their location, cuisine, ratings, and other attributes. It is particularly useful for applications in food and beverage industry analysis, recommendation systems, and geographical studies.", "## Dataset Structure\n\nEach record in the dataset represents a single restaurant and contains the following fields:\n\n- '_id': A unique identifier for the restaurant record.\n- 'address': An object containing the building number, coordinates, street, and zipcode of the restaurant.\n- 'borough': The borough in which the restaurant is located.\n- 'cuisine': The type of cuisine offered by the restaurant.\n- 'name': The name of the restaurant.\n- 'restaurant_id': A unique restaurant ID.\n- 'location': Geolocation data of the restaurant, in 'Point' format.\n- 'stars': The star rating of the restaurant.\n- 'review_count': Number of reviews the restaurant has received.\n- 'attributes': Various attributes of the restaurant, such as 'GoodForKids', 'RestaurantsDelivery', 'NoiseLevel', etc.\n- 'PriceRange': The price range of the restaurant.\n- 'OutdoorSeating': Indicates whether the restaurant has outdoor seating.\n- 'HappyHour': Indicates whether the restaurant offers a happy hour.\n- 'TakeOut': Indicates whether the restaurant offers takeout services.\n- 'DogsAllowed': Indicates whether dogs are allowed in the restaurant.\n- 'embedding': A list of numerical values representing the embedding of the menu and attributes.", "## Field Details", "### Address Object\n\n- 'building': Building number.\n- 'coord': Array containing longitude and latitude.\n- 'street': Street name.\n- 'zipcode': Postal code.", "### Location Object\n\n- 'type': Type of the geolocation data, typically '\"Point\"'.\n- 'coordinates': Array containing longitude and latitude.", "### Attributes Object\n\n- This object contains several boolean and string fields representing various features and services of the restaurant, such as 'GoodForKids', 'RestaurantsDelivery', 'NoiseLevel', etc.", "### Embedding Field\n\n- Generated by OpenAI 'text-embedding-3-small' with 256 elements. This field consists of an array of floating point numbers. It represents a combined embedding of the restaurant's menu and attributes, useful for similarity searches and machine learning applications.", "## Usage\n\nThis dataset can be utilized for various purposes, including but not limited to:\n\n- Analysis of restaurant trends in different boroughs.\n- Development of recommendation systems based on cuisine, attributes, and location.\n- Geospatial analysis of restaurant distributions.", "## Notes\n\n- The dataset is provided \"as is\" and is intended for informational purposes only.\n- Users are advised to consider the implications of the embedded data and its use in their applications.", "### Sample Document", "## Ingest Data\n\nThe small script 'URL' can be used to load the data into your MongoDB Atlas cluster. \n\n\nThe 'URL':", "## Contact\n\nFor any queries or further information regarding this dataset, please open a disucssion." ]

[ "TAGS\n#language-English #license-apache-2.0 #region-us \n", "# Whatscooking.restaurants", "## Overview\n\nThis dataset provides detailed information about various restaurants, including their location, cuisine, ratings, and other attributes. It is particularly useful for applications in food and beverage industry analysis, recommendation systems, and geographical studies.", "## Dataset Structure\n\nEach record in the dataset represents a single restaurant and contains the following fields:\n\n- '_id': A unique identifier for the restaurant record.\n- 'address': An object containing the building number, coordinates, street, and zipcode of the restaurant.\n- 'borough': The borough in which the restaurant is located.\n- 'cuisine': The type of cuisine offered by the restaurant.\n- 'name': The name of the restaurant.\n- 'restaurant_id': A unique restaurant ID.\n- 'location': Geolocation data of the restaurant, in 'Point' format.\n- 'stars': The star rating of the restaurant.\n- 'review_count': Number of reviews the restaurant has received.\n- 'attributes': Various attributes of the restaurant, such as 'GoodForKids', 'RestaurantsDelivery', 'NoiseLevel', etc.\n- 'PriceRange': The price range of the restaurant.\n- 'OutdoorSeating': Indicates whether the restaurant has outdoor seating.\n- 'HappyHour': Indicates whether the restaurant offers a happy hour.\n- 'TakeOut': Indicates whether the restaurant offers takeout services.\n- 'DogsAllowed': Indicates whether dogs are allowed in the restaurant.\n- 'embedding': A list of numerical values representing the embedding of the menu and attributes.", "## Field Details", "### Address Object\n\n- 'building': Building number.\n- 'coord': Array containing longitude and latitude.\n- 'street': Street name.\n- 'zipcode': Postal code.", "### Location Object\n\n- 'type': Type of the geolocation data, typically '\"Point\"'.\n- 'coordinates': Array containing longitude and latitude.", "### Attributes Object\n\n- This object contains several boolean and string fields representing various features and services of the restaurant, such as 'GoodForKids', 'RestaurantsDelivery', 'NoiseLevel', etc.", "### Embedding Field\n\n- Generated by OpenAI 'text-embedding-3-small' with 256 elements. This field consists of an array of floating point numbers. It represents a combined embedding of the restaurant's menu and attributes, useful for similarity searches and machine learning applications.", "## Usage\n\nThis dataset can be utilized for various purposes, including but not limited to:\n\n- Analysis of restaurant trends in different boroughs.\n- Development of recommendation systems based on cuisine, attributes, and location.\n- Geospatial analysis of restaurant distributions.", "## Notes\n\n- The dataset is provided \"as is\" and is intended for informational purposes only.\n- Users are advised to consider the implications of the embedded data and its use in their applications.", "### Sample Document", "## Ingest Data\n\nThe small script 'URL' can be used to load the data into your MongoDB Atlas cluster. \n\n\nThe 'URL':", "## Contact\n\nFor any queries or further information regarding this dataset, please open a disucssion." ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of ibivibiv/orthorus-125b-moe-v2\n\n\n\nDataset automatically created during the evaluation run of model ibivibiv/orthorus-125b-moe-v2 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 1 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 2024-02-06T15:03:25.094734(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 ibivibiv/orthorus-125b-moe-v2\n\n\n\nDataset automatically created during the evaluation run of model ibivibiv/orthorus-125b-moe-v2 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 1 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 2024-02-06T15:03:25.094734(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" ]

[ "region:us" ]

[]

[]

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

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

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

[]

[]

[ "# Text to Image Dataset for Pixel Art style", "## Dataset Description\n\nThe dataset contains 100 examples of Images representing different topics all with the same style." ]

[ "TAGS\n#task_categories-text-to-image #license-mit #region-us \n", "# Text to Image Dataset for Pixel Art style", "## Dataset Description\n\nThe dataset contains 100 examples of Images representing different topics all with the same style." ]

[ "prodigy", "region:us" ]

[]

[]

[ "# Dataset Card for Dataset Name", "## 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#prodigy #region-us \n", "# Dataset Card for Dataset Name", "## 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:graph-ml", "size_categories:1K<n<10K", "license:cc", "art", "arxiv:2210.02016", "region:us" ]

[ "2210.02016" ]

[]

[]

[ "TAGS\n#task_categories-graph-ml #size_categories-1K<n<10K #license-cc #art #arxiv-2210.02016 #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_qa\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_qa\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_doc\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_doc\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_docidx\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_docidx\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_doc_qa\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_doc_qa\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_recite_qa\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_recite_qa\"\n\nMore Information needed" ]