Datasets:

librarian-bots

/

dataset_cards_with_metadata

like 11

mask-distilled-libri-one-sec-cv12/chunk_77

mask-distilled-libri-one-sec-cv12

--- dataset_info: features: - name: audio dtype: audio: sampling_rate: 16000 - name: logits sequence: float32 splits: - name: train num_bytes: 204441040.12812355 num_examples: 6377 download_size: 177590726 dataset_size: 204441040.12812355 configs: - config_name: default data_files: - split: train path: data/train-* ---

justice-416/llama3-tt01

justice-416

--- license: apache-2.0 ---

mask-distilled-libri-one-sec-cv12/chunk_81

mask-distilled-libri-one-sec-cv12

--- dataset_info: features: - name: audio dtype: audio: sampling_rate: 16000 - name: logits sequence: float32 splits: - name: train num_bytes: 246310257.39476988 num_examples: 7683 download_size: 211683419 dataset_size: 246310257.39476988 configs: - config_name: default data_files: - split: train path: data/train-* ---

qiqiqiqiqiq/test4

qiqiqiqiqiq

--- license: apache-2.0 ---

Thauan12/rezendeevil

Thauan12

--- license: openrail ---

justice-416/llama3-002

justice-416

--- license: apache-2.0 ---

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_3

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train_prefs num_bytes: 40300954 num_examples: 4850 download_size: 22391996 dataset_size: 40300954 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_3" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_2

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train_prefs num_bytes: 39928251 num_examples: 4850 download_size: 22115477 dataset_size: 39928251 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_2" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_1

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train_prefs num_bytes: 40878580 num_examples: 4850 download_size: 22657434 dataset_size: 40878580 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_1" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_0

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train_prefs num_bytes: 40588036 num_examples: 4850 download_size: 22609569 dataset_size: 40588036 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_train_part_2_mini_0" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_2

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train_prefs num_bytes: 161695821 num_examples: 19400 download_size: 89823496 dataset_size: 161695821 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_train_part_2" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

0x7o/quality-dataset

0x7o

--- dataset_info: features: - name: label dtype: int64 - name: text dtype: string splits: - name: train num_bytes: 641696533.8850998 num_examples: 52337 - name: test num_bytes: 160433329.11490017 num_examples: 13085 download_size: 389335852 dataset_size: 802129863.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

ngoc/protonx-pokemon-challenge

ngoc

--- license: apache-2.0 ---

recursal/SuperWiki-1.5

recursal

--- annotations_creators: - no-annotation language_creators: - crowdsourced license: - cc-by-sa-3.0 task_categories: - text-generation - fill-mask task_ids: - language-modeling - masked-language-modeling source_datasets: - original language: - ar - de - en - es - fa - fr - he - hi - id - it - ja - ko - nl - pl - pt - ru - sv - tr - uk - vi - zh pretty_name: SuperWIKI v1.5 --- ## Dataset Details  *Waifu to catch your attention.* ### Dataset Description *SuperWIKI-1.5* is a **~18.23B** Tokens (llama-2-7b-chat-tokenizer) / **~15.17B** Tokens (RWKV Tokenizer) multilingual dataset of Wikipedia articles, curated from Wikipedia HTML dumps. It serves as a training resource for large language models and other NLP tasks. This card details the dataset's origin, content, and limitations. - **Curated by:** KaraKaraWitch - **Funded by:** Recursal.ai (I work there lol) - **Shared by:** KaraKaraWitch - **Language(s) (NLP):** Multiple (see Supported Languages) - **License:** cc-by-sa-4.0 SuperWIKI-1.5 was created under time constraints for the release of [EagleX v1](https://huggingface.co/recursal/EagleX_1-7T_HF), and may contain biases in selection. **We highly recommend using the improved version, *SuperWikipedia-NEXT* instead.** ### Dataset Summary Wikipedia dataset containing cleaned articles of all languages. The dataset is manually built from Wikipedia HTML dumps with each split for each language. Each example contains the content of one full Wikipedia article. ### Supported Tasks and Leaderboards Primarily used for language modeling ### Languages The dataset includes Wikipedia articles from the following languages: ``` ar.wikipedia.org de.wikipedia.org en.wikipedia.org es.wikipedia.org fa.wikipedia.org fr.wikipedia.org he.wikipedia.org hi.wikipedia.org id.wikipedia.org it.wikipedia.org ja.wikipedia.org ko.wikipedia.org nl.wikipedia.org pl.wikipedia.org pt.wikipedia.org ru.wikipedia.org simple.wikipedia.org sv.wikipedia.org tr.wikipedia.org uk.wikipedia.org vi.wikipedia.org zh.wikipedia.org ``` *`.wikipedia.org`* extensions have been added for your convenience. ### Selection Bias Unlike SuperWikipedia-NEXT, the language selection in SuperWIKI-1.5 was manual and may favor certain languages (e.g., CJK and European languages). ### Filtering The filtering process is documented in code but not well-organized. We recommend reviewing the code directly for details. ### Data Instances Refer to this sample to see all the fields: ```json { "id": 4024053, "title": "Tharman Shanmugaratnam", "url": "https://en.wikipedia.org/wiki/Tharman_Shanmugaratnam", "stub": false, "template": [ "Efn", "C-SPAN", "S-aft", "S-new", "Reflist", "Cite news", "S-par", "Cite journal", "Short description", "EngvarB" ], "category": [ "Finance ministers of Singapore", "Singaporean Hindus", "Alumni of Wolfson College, Cambridge", "Deputy Prime Ministers of Singapore", "Ministers for Manpower of Singapore", "Presidents of Singapore", "Singaporean people of Sri Lankan descent", "Singaporean people of Tamil descent", "Articles with WorldCat Entities identifiers", "Articles with GND identifiers", "Articles with VIAF identifiers", ], "license": [ "Creative Commons Attribution Share Alike 3.0 Unported" ], "wikitext": "<...TRUNCATED SAMPLE...> '''Tharman Shanmugaratnam'''{{efn|{{lang-ta|தர்மன் சண்முகரத்தினம்}}}} (born 25 February 1957), also known [[mononymously]] as '''Tharman''', is a Singaporean politician and economist who has been serving as the ninth [[president of Singapore]] since 2023 after winning the [[2023 Singaporean presidential election|2023 presidential election]].\n\nPrior to his presidency, Tharman served as [[Senior Minister of Singapore]] between 2019 and 2023, [[Coordinating Minister for Social Policies (Singapore)|Coordinating Minister for Social Policies]] between 2015 and 2023, and Chairman of the [[Monetary Authority of Singapore]] between 2011 and 2023.<ref name=\"Parliament Profile\"/> \n\nTharman is an economist in roles principally related to economic and social policies. He has also led various international councils and panels simultaneously. Tharman chairs the Board of Trustees of the [[Group of Thirty]], a global council of economic and financial leaders from the public and private sectors and academia. He also co-chairs the Global Commission on the Economics of Water with [[Ngozi Okonjo-Iweala|Ngozi Owonjo-Iweala]], [[Mariana Mazzucato]] and [[Johan Rockström]]. Its initial recommendations helped shape the outcomes of the UN Water Conference in March 2023. Tharman has also been co-chair of the [[G20]] High Level Independent Panel on Global Financing for Pandemic Preparedness and Response since 2021. In 2017, Tharman was appointed to chair the G20 Eminent Persons Group on Global Financial Governance.\n\nA former member of the governing [[People's Action Party]] (PAP), he was the... <...TRUNCATED SAMPLE...>", "lang": "en", "abstract": "Tharman Shanmugaratnam, also known mononymously as Tharman, is a Singaporean politician and economist who has been serving as the ninth president of Singapore since 2023. Prior to his presidency, Tharman served as Senior Minister of Singapore between 2019 and 2023, Coordinating Minister for Social Policies between 2015 and 2023, and Chairman of the Monetary Authority of Singapore between 2011 and 2023. Tharman is an economist in roles principally related to economic and social policies. He has also led various international councils and panels simultaneously. Tharman chairs the Board of Trustees of the Group of Thirty, a global council of economic and financial leaders from the public and private sectors and academia. He also co-chairs the Global Commission on the Economics of Water with Ngozi Owonjo-Iweala, Mariana Mazzucato and Johan Rockström. Its initial recommendations helped shape the outcomes of the UN Water Conference in March 2023. Tharman has also been co-chair of the G20 High Level Independent Panel on Global Financing for Pandemic Preparedness and Response since 2021. In 2017, Tharman was appointed to chair the G20 Eminent Persons Group on Global Financial Governance. <...TRUNCATED SAMPLE...>", "boxes_filters": [], "infobox_html": [ "<...TRUNCATED SAMPLE...>" ], "figures_dict": [ { "file_url": "./File:Mr_Tharman_at_Bloomberg_New_Economy_Forum.jpg", "caption": "" } ], "text": "9th President of Singapore\n\n\n**Tharman Shanmugaratnam** (born 25 February 1957), also known mononymously as **Tharman**, is a Singaporean politician and economist who has been serving as the ninth president of Singapore since 2023. Prior to his presidency, Tharman served as Senior Minister of Singapore between 2019 and 2023, Coordinating Minister for Social Policies between 2015 and 2023, and Chairman of the Monetary Authority of Singapore between 2011 and 2023.\n\nTharman is an economist in roles principally related to economic and social policies. He has also led various international councils and panels simultaneously. <...TRUNCATED SAMPLE...>" } ``` ### Data Fields `id`: The article ID in question `title`: The title of the Wikipedia article. `url`: The URL of the article. `stub`: A boolean (true/false) flag marked as a stub from the CSS selector `.metadata.plainlinks`. `template`: A list of templates found in the article. `text`: The HTML Text (After post-processing) from SuperWIKI converted to Markdown with links removed and formatting (Bold, italics) kept. `license`: The license for the article. `wikitext`: The wikitext. Not used but can be used as a reference. `lang`: The language. Should be the same as wiki. (For `simplewiki` it should be `en`) `boxes_filters`: Also known as `rituals` found in the original SuperWIKI. These are extracted from the CSS selectors `.ombox` and `.ambox`. `infobox_html`: A list of side infoboxes that are extracted out from the text. `figures_dict`: A list of figures used in the article. Again, extracted out from the text. `text`: The Markdown text. This is what you should probably use or need for LLM training. ## Recursal's Vision > To make AI accessible to everyone, regardless of language, or economical status This is the collective goal of the `RWKV Open Source foundation` and `Recursal AI`, the commercial entity who backs it. We believe that AI should not be controlled by a select few individual organization. And that it should be made accessible regardless if you are rich or poor, or a native speaker of english. ### About RWKV RWKV is an Open Source, non profit group, under the linux foundation. Focused on developing the RWKV AI architecture, in accordence to our vision. The RWKV architecture scales efficiently and economically. As an RNN & Transformer hybrid, it is able to provide the performance similar to leading transformer models, while having the compute and energy efficiency of an RNN based architecture. You can find out more about the project, and latest models, at the following - [https://blog.rwkv.com](https://blog.rwkv.com) - [https://wiki.rwkv.com](https://wiki.rwkv.com) ### About Recursal AI Recursal AI, is the commercial entity built to provide support for RWKV model development and users, while providing commercial services via its public cloud, or private-cloud / on-premise offerings. As part of our vision. Our commitment, is to ensure open source development and access to the best foundational AI models and datasets. The following dataset/models provided here, is part of that commitment. You can find out more about recursal AI here - [https://recursal.ai](https://recursal.ai) - [https://blog.recursal.ai](https://blog.recursal.ai) ### Dataset Curators KaraKaraWitch. (I typically hang out in PygmalionAI discord, sometimes EleutherAI. If something is wrong, `@karakarawitch` on discord.) I'd be happy if you could spread the word and recommend this dataset over wikitext for your use cases `:)` ### Licensing Information Most of Wikipedia's text and many of its images are co-licensed under the [Creative Commons Attribution-ShareAlike 3.0 Unported License](https://en.wikipedia.org/wiki/Wikipedia:Text_of_Creative_Commons_Attribution-ShareAlike_3.0_Unported_License) (CC BY-SA) and the [GNU Free Documentation License](https://en.wikipedia.org/wiki/Wikipedia:Text_of_the_GNU_Free_Documentation_License) (GFDL) (un-versioned, with no invariant sections, front-cover texts, or back-cover texts). Some text has been imported only under CC BY-SA and CC BY-SA-compatible license and cannot be reused under GFDL; such text will be identified on the page footer, in the page history, or on the discussion page of the article that utilizes the text. Recursal Waifus (The banner image) are licensed under CC-BY-SA. They do not represent the related websites in any official capacity unless otherwise or announced by the website. You may use them as a banner image. However, you must always link back to the dataset. ### Citation Information ``` @misc{superwiki, title = {SuperWIKI-1.5}, author = {KaraKaraWitch, recursal.ai}, year = {2024}, howpublished = {\url{https://huggingface.co/datasets/recursal/SuperWiki-1.5}}, } ```

chansung/llamaduo-dataset

chansung

--- license: apache-2.0 ---

WendyBao/finetune_train_20240509

WendyBao

--- dataset_info: features: - name: instruction dtype: string - name: input dtype: string - name: output dtype: string - name: text dtype: string splits: - name: train num_bytes: 482396 num_examples: 702 - name: test num_bytes: 243247 num_examples: 297 download_size: 378084 dataset_size: 725643 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

WendyBao/finetune_20240509

WendyBao

--- dataset_info: features: - name: instruction dtype: string - name: input dtype: string - name: output dtype: string - name: text dtype: string splits: - name: train num_bytes: 482396 num_examples: 702 - name: test num_bytes: 243247 num_examples: 297 download_size: 378084 dataset_size: 725643 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

guilhermebastos96/francisca_1000_balanceado

guilhermebastos96

--- dataset_info: features: - name: speaker_id dtype: int64 - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string splits: - name: train num_bytes: 354248737.0 num_examples: 1000 download_size: 342124813 dataset_size: 354248737.0 --- # Dataset Card for "francisca_1000_balanceado" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

ura-hcmut/Generated-texts-Llama-2-7b-hf-arc_challenge

ura-hcmut

--- dataset_info: features: - name: Prompt dtype: string - name: Generated_Text_1 dtype: string - name: Generated_Text_2 dtype: string - name: Generated_Text_3 dtype: string - name: Generated_Text_4 dtype: string - name: Generated_Text_5 dtype: string - name: Generated_Text_6 dtype: string - name: Generated_Text_7 dtype: string - name: Generated_Text_8 dtype: string - name: Generated_Text_9 dtype: string - name: Generated_Text_10 dtype: string - name: Generated_Text_11 dtype: string - name: Generated_Text_12 dtype: string - name: Generated_Text_13 dtype: string - name: Generated_Text_14 dtype: string - name: Generated_Text_15 dtype: string - name: Generated_Text_16 dtype: string - name: Generated_Text_17 dtype: string - name: Generated_Text_18 dtype: string - name: Generated_Text_19 dtype: string - name: Generated_Text_20 dtype: string - name: Generated_Text_21 dtype: string - name: Generated_Text_22 dtype: string - name: Generated_Text_23 dtype: string - name: Generated_Text_24 dtype: string - name: Generated_Text_25 dtype: string - name: Generated_Text_26 dtype: string - name: Generated_Text_27 dtype: string - name: Generated_Text_28 dtype: string - name: Generated_Text_29 dtype: string - name: Generated_Text_30 dtype: string - name: Generated_Text_31 dtype: string - name: Generated_Text_32 dtype: string - name: Generated_Text_33 dtype: string - name: Generated_Text_34 dtype: string - name: Generated_Text_35 dtype: string - name: Generated_Text_36 dtype: string - name: Generated_Text_37 dtype: string - name: Generated_Text_38 dtype: string - name: Generated_Text_39 dtype: string - name: Generated_Text_40 dtype: string - name: Generated_Text_41 dtype: string - name: Generated_Text_42 dtype: string - name: Generated_Text_43 dtype: string - name: Generated_Text_44 dtype: string - name: Generated_Text_45 dtype: string - name: Generated_Text_46 dtype: string - name: Generated_Text_47 dtype: string - name: Generated_Text_48 dtype: string - name: Generated_Text_49 dtype: string - name: Generated_Text_50 dtype: string - name: Generated_Text_51 dtype: string - name: Generated_Text_52 dtype: string - name: Generated_Text_53 dtype: string - name: Generated_Text_54 dtype: string - name: Generated_Text_55 dtype: string - name: Generated_Text_56 dtype: string - name: Generated_Text_57 dtype: string - name: Generated_Text_58 dtype: string - name: Generated_Text_59 dtype: string - name: Generated_Text_60 dtype: string - name: Generated_Text_61 dtype: string - name: Generated_Text_62 dtype: string - name: Generated_Text_63 dtype: string - name: Generated_Text_64 dtype: string - name: Generated_Text_65 dtype: string - name: Generated_Text_66 dtype: string - name: Generated_Text_67 dtype: string - name: Generated_Text_68 dtype: string - name: Generated_Text_69 dtype: string - name: Generated_Text_70 dtype: string - name: Generated_Text_71 dtype: string - name: Generated_Text_72 dtype: string - name: Generated_Text_73 dtype: string - name: Generated_Text_74 dtype: string - name: Generated_Text_75 dtype: string - name: Generated_Text_76 dtype: string - name: Generated_Text_77 dtype: string - name: Generated_Text_78 dtype: string - name: Generated_Text_79 dtype: string - name: Generated_Text_80 dtype: string - name: Generated_Text_81 dtype: string - name: Generated_Text_82 dtype: string - name: Generated_Text_83 dtype: string - name: Generated_Text_84 dtype: string - name: Generated_Text_85 dtype: string - name: Generated_Text_86 dtype: string - name: Generated_Text_87 dtype: string - name: Generated_Text_88 dtype: string - name: Generated_Text_89 dtype: string - name: Generated_Text_90 dtype: string - name: Generated_Text_91 dtype: string - name: Generated_Text_92 dtype: string - name: Generated_Text_93 dtype: string - name: Generated_Text_94 dtype: string - name: Generated_Text_95 dtype: string - name: Generated_Text_96 dtype: string - name: Generated_Text_97 dtype: string - name: Generated_Text_98 dtype: string - name: Generated_Text_99 dtype: string - name: Generated_Text_100 dtype: string splits: - name: train num_bytes: 537375511 num_examples: 3357 download_size: 202841655 dataset_size: 537375511 configs: - config_name: default data_files: - split: train path: data/train-* ---

SoumyaM/databricks-micro

SoumyaM

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 5206498 num_examples: 10544 download_size: 3149915 dataset_size: 5206498 configs: - config_name: default data_files: - split: train path: data/train-* ---

vishheartT/dataset_formatted

vishheartT

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 712 num_examples: 4 download_size: 1688 dataset_size: 712 configs: - config_name: default data_files: - split: train path: data/train-* ---

SeyedAli/Image-Valence-Arousal-continous-class

SeyedAli

--- configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* dataset_info: features: - name: image dtype: image - name: Arousal dtype: float64 - name: Valence dtype: float64 splits: - name: train num_bytes: 742641757.5 num_examples: 8612 - name: test num_bytes: 186137091.75 num_examples: 2154 download_size: 0 dataset_size: 928778849.25 --- # Dataset Card for "Image-Valence-Arousal-continous-class" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

kenken999/urlounge

kenken999

--- license: mit task_categories: - text-classification language: - ja tags: - finance pretty_name: te ---

changliu8541/Assemblage_vcpkgDLL

changliu8541

--- license: other --- # Assemblage vcpkg DLL Dataset _{last updated: June 16th} This reposotory holds the public dataset for [Assemblage](https://assemblage-dataset.net/), this copy of dataset is on vcpkg dll data along with pdb files. Please note, the Assemblage code is published under the MIT license, while the dataset specify each binary's source code repository license, please adhere to original repository's license. You can find the paper on [arxiv](https://arxiv.org/abs/2405.03991). Please use cat (the command, not my cat) to concatenate part files into the original xz file, then unzip it. ``` # Concat the SQLite database then uncompress it cat vcpkg.sqlite.tar.xz.* > vcpkg.sqlite.tar.xz tar -xvf vcpkg.sqlite.tar.xz ``` ### Dataset Details This public copy of Assemblage data consists of 130k vcpkg DLL binaries, and the information are stored in the SQLite database. Due to the nature that binary files can't be represented as texts, a seperate `vcpkg_final.tar.xz` is included, after inflation the folder contains the bnary files. Each file can be indexed by either its SHA256 hash, by `hash` column or the `binary_path` column. You can also read our [docs on dataset](https://assemblagedocs.readthedocs.io/en/latest/dataset.html)

usableteapot/all-v2

usableteapot

--- dataset_info: features: - name: model dtype: string - name: conversation list: - name: content dtype: string - name: role dtype: string - name: source dtype: string - name: tokens sequence: int64 - name: token_count dtype: int64 - name: model_category dtype: string splits: - name: train num_bytes: 42110619386.0 num_examples: 3690835 download_size: 12997633665 dataset_size: 42110619386.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

rollerhafeezh-amikom/sk_nergrit_corpus

rollerhafeezh-amikom

--- configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* - split: validation path: data/validation-* dataset_info: features: - name: id dtype: string - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-LOC '2': I-LOC '3': B-DAT '4': I-DAT '5': B-TIM '6': I-TIM splits: - name: train num_bytes: 3236767 num_examples: 6611 - name: test num_bytes: 660730 num_examples: 1228 - name: validation num_bytes: 626094 num_examples: 1251 download_size: 1140052 dataset_size: 4523591 --- # Dataset Card for "sk_nergrit_corpus" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

rollerhafeezh-amikom/id_nergrit_corpus

rollerhafeezh-amikom

--- configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* - split: validation path: data/validation-* dataset_info: features: - name: id dtype: string - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-LOC '2': I-LOC '3': B-DAT '4': I-DAT '5': B-TIM '6': I-TIM splits: - name: train num_bytes: 2863630.192227897 num_examples: 6611 - name: test num_bytes: 581270.9078782826 num_examples: 1228 - name: validation num_bytes: 539116.4898849663 num_examples: 1251 download_size: 677131 dataset_size: 3984017.589991146 --- # Dataset Card for "id_nergrit_corpus" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

trungdang2901/dattta

trungdang2901

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 10787543066 num_examples: 75318247 download_size: 6218841142 dataset_size: 10787543066 configs: - config_name: default data_files: - split: train path: data/train-* ---

sagwa/train1

sagwa

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 5826 num_examples: 39 download_size: 2572 dataset_size: 5826 configs: - config_name: default data_files: - split: train path: data/train-* ---

rmsdud/complaints_small_data

rmsdud

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 3788379 num_examples: 2844 download_size: 2030454 dataset_size: 3788379 configs: - config_name: default data_files: - split: train path: data/train-* ---

ndiy/ASAP_SENT

ndiy

--- dataset_info: features: - name: label dtype: int32 - name: text dtype: string splits: - name: train num_bytes: 34566868 num_examples: 36850 - name: test num_bytes: 4635605 num_examples: 4940 download_size: 27770214 dataset_size: 39202473 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

amilmshaji/onepane-llm-evaluation-gemini

amilmshaji

--- dataset_info: features: - name: id dtype: int64 - name: question dtype: string - name: context dtype: string - name: response dtype: string - name: model_name dtype: string - name: latency dtype: float64 - name: pricing dtype: float64 - name: input_token_lenght dtype: int64 - name: output_token_length dtype: int64 splits: - name: train num_bytes: 75304 num_examples: 20 download_size: 38242 dataset_size: 75304 configs: - config_name: default data_files: - split: train path: data/train-* ---

WSTR/gender_annotation

WSTR

--- license: unknown ---

ccvl/3D-DST-data

ccvl

--- license: mit pretty_name: 3D-DST-models extra_gated_fields: Name: text Affiliation: text --- ## 3D-DST-data As part of our data release in [3D-DST](https://ccvl.jhu.edu/3D-DST/), we present 3D-DST images for all 1000 classes in ImageNet-1k with **MiniGPT4-generated captions** available [here](https://huggingface.co/datasets/ccvl/3D-DST-captions). See [wufeim/DST3D](https://github.com/wufeim/DST3D) for reproduction instructions and [DeiT-small](https://github.com/facebookresearch/deit/blob/main/README_deit.md) results.

artificialnoob/weights

artificialnoob

--- license: mit ---

zoohun/medical_re_one

zoohun

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 1543268 num_examples: 2000 download_size: 360246 dataset_size: 1543268 configs: - config_name: default data_files: - split: train path: data/train-* ---

zoohun/medical_re_two

zoohun

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 1595151 num_examples: 2000 download_size: 371968 dataset_size: 1595151 configs: - config_name: default data_files: - split: train path: data/train-* ---

zoohun/medical_re_three

zoohun

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 1650067 num_examples: 3037 download_size: 378122 dataset_size: 1650067 configs: - config_name: default data_files: - split: train path: data/train-* ---

zoohun/medical_re_four

zoohun

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 815532 num_examples: 1037 download_size: 201675 dataset_size: 815532 configs: - config_name: default data_files: - split: train path: data/train-* ---

qianzhicheng111/TDataSet

qianzhicheng111

--- license: apache-2.0 ---

ndiy/NLPCC14

ndiy

--- dataset_info: features: - name: label dtype: int64 - name: text dtype: string splits: - name: train num_bytes: 4972014 num_examples: 19146 - name: test num_bytes: 385017 num_examples: 1200 download_size: 3837130 dataset_size: 5357031 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

denizzhansahin/deneme1

denizzhansahin

--- dataset_info: features: - name: review dtype: string - name: review_length dtype: int64 splits: - name: train num_bytes: 2109125.3019502354 num_examples: 1338 - name: validation num_bytes: 234872.69804976461 num_examples: 149 download_size: 1387102 dataset_size: 2343998.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---

0xscope/event_rules

0xscope

--- license: mit --- ## 0xScope Event Trading Dataset Rules & Explaination This is the description of the meaning of each event. - Event ID - Event Category - Event Details In addition to these parameters, you will also notice the following parameters: - Token: the address of the token - Chain: the chain of the token - pt: event occurrence time, by hour - Basescore: the expected influence on the token (1: bullish, -1: bearish)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_2

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: resp0 dtype: string - name: resp1 dtype: string - name: resp2 dtype: string - name: resp3 dtype: string splits: - name: train_prefs num_bytes: 65120883 num_examples: 4983 download_size: 36311143 dataset_size: 65120883 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_2" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_3

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: resp0 dtype: string - name: resp1 dtype: string - name: resp2 dtype: string - name: resp3 dtype: string splits: - name: train_prefs num_bytes: 66293811 num_examples: 5086 download_size: 36949341 dataset_size: 66293811 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_3" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_1

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: resp0 dtype: string - name: resp1 dtype: string - name: resp2 dtype: string - name: resp3 dtype: string splits: - name: train_prefs num_bytes: 67659037 num_examples: 5283 download_size: 37873922 dataset_size: 67659037 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_1" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_0

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: resp0 dtype: string - name: resp1 dtype: string - name: resp2 dtype: string - name: resp3 dtype: string splits: - name: train_prefs num_bytes: 68335595 num_examples: 5283 download_size: 38355781 dataset_size: 68335595 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_vllm_part_3_mini_0" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

Xzaxx/Xix-Z

Xzaxx

--- license: mit ---

NickyNicky/financial_phrasebank_traslate_En_Es

NickyNicky

--- dataset_info: features: - name: sentence_en dtype: string - name: sentence_es dtype: string - name: label dtype: int64 splits: - name: train num_bytes: 1389599 num_examples: 4830 download_size: 816379 dataset_size: 1389599 configs: - config_name: default data_files: - split: train path: data/train-* license: apache-2.0 task_categories: - translation language: - en - es tags: - finance size_categories: - 1K<n<10K --- ## time traslation.  ## labels. * Negativo: 0 * Neutral: 1 * Positivo: 2 ## model use for traslation. ``` https://huggingface.co/NickyNicky/gemma-1.1-2b-it_orpo_traslate_en_es_V1 ``` ## original dataset: ``` https://huggingface.co/datasets/financial_phrasebank ```

mawadalla/tatoeba_large

mawadalla

--- size_categories: - 1M<n<10M --- A dataset of 8 million sentences in hundreds of languages, crowd sourced from tatoeba.

soaple/custom-llama2

soaple

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 7754 num_examples: 32 download_size: 4170 dataset_size: 7754 configs: - config_name: default data_files: - split: train path: data/train-* ---

bipinsaha/bangla-law-qna

bipinsaha

--- license: cc-by-nc-4.0 ---

xieyuankun/Codecfake

xieyuankun

--- license: cc-by-nc-3.0 dataset_info: features: - name: audio dtype: audio splits: - name: train num_bytes: 1280756603.44 num_examples: 8887 download_size: 2068524987 dataset_size: 1280756603.44 configs: - config_name: default data_files: - split: train path: data/train-* ---

niklauslee/customllama2

niklauslee

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 7754 num_examples: 32 download_size: 4170 dataset_size: 7754 configs: - config_name: default data_files: - split: train path: data/train-* ---

heegyu/UltraInteract_pair_subtree

heegyu

--- dataset_info: features: - name: parent struct: - name: chosen dtype: string - name: dataset dtype: string - name: depth dtype: int64 - name: id dtype: string - name: parent_id dtype: string - name: rejected dtype: string - name: task dtype: string - name: trajectory list: - name: from dtype: string - name: value dtype: string - name: child struct: - name: chosen dtype: string - name: dataset dtype: string - name: depth dtype: int64 - name: id dtype: string - name: parent_id dtype: string - name: rejected dtype: string - name: task dtype: string - name: trajectory list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 707433702 num_examples: 59603 download_size: 176485453 dataset_size: 707433702 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "UltraInteract_pair_subtree" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

AndrewZeng/train_only_twice_syn

AndrewZeng

--- license: apache-2.0 ---

AndrewZeng/train_only_third_syn

AndrewZeng

--- license: apache-2.0 ---

AndrewZeng/train_only_forth_syn

AndrewZeng

--- license: apache-2.0 ---

irisxue/childrens_book_covers

irisxue

--- configs: - config_name: default data_files: - split: train path: data/train-* dataset_info: features: - name: image dtype: image - name: text dtype: string splits: - name: train num_bytes: 917850.0 num_examples: 100 download_size: 926704 dataset_size: 917850.0 ---

swyoo39/customData

swyoo39

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 5826 num_examples: 39 download_size: 2572 dataset_size: 5826 configs: - config_name: default data_files: - split: train path: data/train-* ---

Spico/Mirror_ACE

Spico

--- language: - en --- # Mirror Dataset (ACE Part) This is the rest part of the whole datasets for [🪞Mirror](https://github.com/Spico197/Mirror). You could merge with [Mirror_woACE](https://huggingface.co/datasets/Spico/Mirror_woACE) to get the complete dataset. This repo mainly contains the ACE dataset that requires an additional LDC license. If you have such a license, please feel free to drop Tong Zhu an email (tzhu1997@outlook.com) with some data samples, then apply the dataset access on this page. Direct data access applications without email notifications will not be approved. ## Citation ```bibtex @misc{zhu_mirror_2023, shorttitle = {Mirror}, title = {Mirror: A Universal Framework for Various Information Extraction Tasks}, author = {Zhu, Tong and Ren, Junfei and Yu, Zijian and Wu, Mengsong and Zhang, Guoliang and Qu, Xiaoye and Chen, Wenliang and Wang, Zhefeng and Huai, Baoxing and Zhang, Min}, url = {http://arxiv.org/abs/2311.05419}, doi = {10.48550/arXiv.2311.05419}, urldate = {2023-11-10}, publisher = {arXiv}, month = nov, year = {2023}, note = {arXiv:2311.05419 [cs]}, keywords = {Computer Science - Artificial Intelligence, Computer Science - Computation and Language}, } ```

uine/single-dpo-practice-dataset

uine

--- dataset_info: features: - name: rejected dtype: string - name: chosen dtype: string - name: prompt dtype: string splits: - name: train num_bytes: 2740378 num_examples: 2109 download_size: 1009085 dataset_size: 2740378 configs: - config_name: default data_files: - split: train path: data/train-* ---

Cafet/Tiny_Train_Processed

Cafet

--- dataset_info: features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription dtype: string - name: reference dtype: string - name: prediction_01 dtype: string splits: - name: train num_bytes: 2837918903.875 num_examples: 10369 download_size: 2539257678 dataset_size: 2837918903.875 configs: - config_name: default data_files: - split: train path: data/train-* ---

Soykot/Godeg

Soykot

--- license: mit ---

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_minpi_part_3

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: resp0 dtype: string - name: resp1 dtype: string - name: resp2 dtype: string - name: resp3 dtype: string - name: minpi dtype: string - name: random dtype: string splits: - name: train_prefs num_bytes: 318778019 num_examples: 20635 download_size: 178621360 dataset_size: 318778019 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_minpi_part_3" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

nirantk/scifact-bge-m3-sparse-vectors

nirantk

--- language: - en license: mit dataset_info: features: - name: _id dtype: string - name: title dtype: string - name: text dtype: string - name: bge_m3_sparse_vector dtype: string splits: - name: corpus num_bytes: 27321636 num_examples: 5183 download_size: 13140473 dataset_size: 27321636 configs: - config_name: default data_files: - split: corpus path: data/corpus-* ---

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_0

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train_prefs num_bytes: 43222850 num_examples: 5158 download_size: 24193117 dataset_size: 43222850 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_0" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_3

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train_prefs num_bytes: 43550584 num_examples: 5161 download_size: 24173607 dataset_size: 43550584 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_3" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_1

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train_prefs num_bytes: 43091603 num_examples: 5158 download_size: 24073161 dataset_size: 43091603 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_1" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_2

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train_prefs num_bytes: 44145884 num_examples: 5158 download_size: 24555538 dataset_size: 44145884 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_train_part_3_mini_2" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

YYYYYYibo/ultrafeedback_binarized_doff_real_no_golden_train_part_3

YYYYYYibo

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train_prefs num_bytes: 174010921 num_examples: 20635 download_size: 96907152 dataset_size: 174010921 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_doff_real_no_golden_train_part_3" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

hotsx/cristiane

hotsx

--- license: openrail ---

manjugeorge/common

manjugeorge

--- license: apache-2.0 ---

jili/tcm

jili

--- license: apache-2.0 ---

llm-values/self_response_2_Qwen__Qwen1.5_110B_answers

llm-values

--- dataset_info: features: - name: prompt ID dtype: int64 - name: language dtype: string - name: topic dtype: string - name: labels sequence: string - name: original prompt dtype: string - name: translated prompt dtype: string - name: 'answer: Qwen/Qwen1.5-110B - original' dtype: string - name: 'answer: Qwen/Qwen1.5-110B - translated' dtype: string - name: pos priming phrase 0 - original dtype: string - name: 'pos priming phrase 0, answer: Yes - original' dtype: string - name: pos priming phrase 0, answer Yes logprob - original dtype: int64 - name: 'pos priming phrase 0, answer: No - original' dtype: string - name: pos priming phrase 0, answer No logprob - original dtype: int64 - name: neg priming phrase 0 - original dtype: string - name: 'neg priming phrase 0, answer: Yes - original' dtype: string - name: neg priming phrase 0, answer Yes logprob - original dtype: int64 - name: 'neg priming phrase 0, answer: No - original' dtype: string - name: neg priming phrase 0, answer No logprob - original dtype: int64 - name: pos priming phrase 0 - translated dtype: string - name: 'pos priming phrase 0, answer: Yes - translated' dtype: string - name: pos priming phrase 0, answer Yes logprob - translated dtype: int64 - name: 'pos priming phrase 0, answer: No - translated' dtype: string - name: pos priming phrase 0, answer No logprob - translated dtype: int64 - name: neg priming phrase 0 - translated dtype: string - name: 'neg priming phrase 0, answer: Yes - translated' dtype: string - name: neg priming phrase 0, answer Yes logprob - translated dtype: int64 - name: 'neg priming phrase 0, answer: No - translated' dtype: string - name: neg priming phrase 0, answer No logprob - translated dtype: int64 splits: - name: self_response_2_Qwen__Qwen1.5_110B_answers num_bytes: 700300 num_examples: 701 download_size: 171337 dataset_size: 700300 configs: - config_name: default data_files: - split: self_response_2_Qwen__Qwen1.5_110B_answers path: data/self_response_2_Qwen__Qwen1.5_110B_answers-* ---

med-alex/qa_mt_en_to_kaz

med-alex

--- task_categories: - question-answering language: - kk size_categories: - 10K<n<100K --- This is one of the datasets created as part of a project to study the solution of the QA problem for low-resource languages using the example of the Kazakh and Uzbek languages. Please see the [description](https://github.com/med-alex/turkic_qa?tab=readme-ov-file#добро-пожаловать-на-студенческий-проект-посвященный-решению-задачи-qa-для-низкоресурсных-языков-на-примере-казахского-и-узбекского-языка) of the project to learn more about the method of creating a dataset. **NOTE:** To achieve the best final models results, you should use similar datasets translated from English: med-alex/qa_mt_en_to_uzn or med-alex/qa_mt_en_to_kaz.

bunkalab/arxiv_datasets_llm

bunkalab

--- dataset_info: features: - name: Title dtype: string - name: Authors dtype: string - name: Abstract dtype: string - name: entry_id dtype: string - name: Date dtype: timestamp[ns, tz=UTC] - name: Categories dtype: string - name: year dtype: int32 splits: - name: train num_bytes: 6037799 num_examples: 3851 download_size: 3297037 dataset_size: 6037799 configs: - config_name: default data_files: - split: train path: data/train-* ---

wisenut-nlp-team/dst_dataset

wisenut-nlp-team

--- dataset_info: features: - name: left_inputs dtype: string - name: right_inputs dtype: string - name: length_labels dtype: int64 - name: task_labels dtype: int64 - name: multiturn_labels dtype: int64 - name: multiquestion_labels sequence: int64 splits: - name: train num_bytes: 76241205 num_examples: 74583 - name: validation num_bytes: 19096089 num_examples: 18646 - name: test num_bytes: 12053756 num_examples: 11444 download_size: 53963164 dataset_size: 107391050 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* ---

wisenut-nlp-team/smr_dataset

wisenut-nlp-team

--- dataset_info: features: - name: passage dtype: string - name: summary dtype: string splits: - name: train num_bytes: 7691192512 num_examples: 899822 - name: validation num_bytes: 810294954 num_examples: 108339 download_size: 3494915664 dataset_size: 8501487466 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---

edizpy/karar-ds-mini_0905_1

edizpy

--- dataset_info: features: - name: text dtype: string - name: karar_uzunluk dtype: int64 splits: - name: train num_bytes: 2424646.93625 num_examples: 3073 - name: validation num_bytes: 269843.5575 num_examples: 342 download_size: 773010 dataset_size: 2694490.49375 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---

Sathviksoma/capitals

Sathviksoma

--- license: openrail ---

Paco4365483/dataset

Paco4365483

--- dataset_info: features: - name: image dtype: image - name: caption dtype: string splits: - name: train num_bytes: 495865.0 num_examples: 9 download_size: 497519 dataset_size: 495865.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

onepaneai/harmful-prompts

onepaneai

--- dataset_info: features: - name: type dtype: string - name: prompt dtype: string splits: - name: train num_bytes: 45720 num_examples: 200 download_size: 22390 dataset_size: 45720 configs: - config_name: default data_files: - split: train path: data/train-* ---

goihere/image-generation-prompting

goihere

--- license: mit split: train path: "dataset - Sheet1 (1).csv" ---

Sathviksoma/captials_answers

Sathviksoma

--- license: openrail ---

irisxue/testing_childrensbooks

irisxue

--- license: mit ---

ikeno-ada/Japanese-English_translation_of_contents_HScodes

ikeno-ada

--- license: mit language: - ja - en --- 日本郵便が提供する「国際郵便　内容品の日英・中英訳、HSコード類」（2024/05/09）のデータに基づいています。 詳しくはサイトをご覧ください https://www.post.japanpost.jp/int/use/publication/contentslist/index.php?id=0&ie=utf8&lang=_ja&q=

Sathviksoma/capitals_formatted

Sathviksoma

--- license: openrail ---

andyWuTw/uozhiba-llama3-tt

andyWuTw

--- license: apache-2.0 ---

Sathviksoma/important_person

Sathviksoma

--- license: openrail ---

chrisx01/tsetse-42

chrisx01

--- license: apache-2.0 ---

talalmuzaffar/empathetic_dataset

talalmuzaffar

--- dataset_info: features: - name: prompt dtype: string - name: utterance dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 1719028 num_examples: 8000 download_size: 954635 dataset_size: 1719028 configs: - config_name: default data_files: - split: train path: data/train-* ---

talalmuzaffar/empathetic_dataset_1

talalmuzaffar

--- dataset_info: features: - name: Input dtype: string - name: Outputs dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 1719028 num_examples: 8000 download_size: 954569 dataset_size: 1719028 configs: - config_name: default data_files: - split: train path: data/train-* ---

talalmuzaffar/empathetic_dataset_2

talalmuzaffar

--- dataset_info: features: - name: Input dtype: string - name: Response dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 1719028 num_examples: 8000 download_size: 954587 dataset_size: 1719028 configs: - config_name: default data_files: - split: train path: data/train-* ---

liswei/PromptPair-TW

liswei

--- language: - zh license: cc-by-nc-sa-4.0 size_categories: - 100K<n<1M task_categories: - text-generation - translation - summarization dataset_info: features: - name: id dtype: int64 - name: conversations list: - name: content dtype: string - name: role dtype: string - name: meta dtype: string splits: - name: train num_bytes: 50151365 num_examples: 119413 download_size: 31222381 dataset_size: 50151365 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for PromptPair-TW - Contains 120K high quality instruction tuning data in Traditional Chinese. - Contains English prompt + Traditional Chinese responses to better adapt from English pre-trained models. - Includes custom system prompts to avoid code-switching after finetuning. - Is de-duplicated and cleaned using both rule-based and learning-based filters. Examples of field `conversations`: ```text [ {"role": "system" , "content": "Explain the following instructions in Traditional Chinese"}, {"role": "user", "content": "Construct a sentence using the given verb in the past tense\n「shudder」"}, {"role": "assistant", "content": "當雷聲在遠處響起時，她不由自主地顫抖了。"} ] ``` ```text [ {"role": "system", "content": "以繁體中文完成此任務"}, {"role": "user", "content": "Suggest two interventions that may reduce drug abuse."}, {"role": "assistant", "content": "兩種可能減少藥物濫用的干預措施是增加諮詢和康復計劃的接觸，以及為學齡兒童實施有關使用藥物風險的教育計劃。諮詢和康復計劃有助於個人確定其成癮的潛在原因和管理渴望的技能，而教育計劃可以幫助青少年更多地了解藥物濫用的潛在後果。"} ] ``` ## System Prompt Details System prompts for en-tw pairs are randomly selected from the following list with 20% dropout: ```text prompts = [ "Please translate the following English paragraph into Traditional Chinese: ", "Translate this text into Traditional Chinese: ", "Convert the English below into Traditional Chinese: ", "Please provide a Traditional Chinese translation of the following text: ", "English to Traditional Chinese translation requested for the paragraph below: ", "Kindly render the English passage below into Traditional Chinese: ", "Turn the following English into Traditional Chinese: ", "English to Traditional Chinese: Please translate the text below: ", "Provide a Traditional Chinese version of the English paragraph below: ", "English text to be translated into Traditional Chinese follows: " "請將以下英文段落翻譯成繁體中文：", "將此文本翻譯成繁體中文：", "把下面的英文翻譯成繁體中文：", "請提供以下文本的繁體中文翻譯：", "請將下列英文段落翻譯為繁體中文：", "以下英文請翻成繁體中文：", "翻譯下面的英文到繁體中文：", "請把以下英文轉譯為繁體中文：", "將下列英文譯為繁體中文：", "英文到繁體中文：請翻譯下面的文本：" ] ``` ## Dataset Details Dataset source: - [ntunlplab/traditional-chinese-alpaca](https://github.com/ntunlplab/traditional-chinese-alpaca): GPT-3.5 generated alpaca instruction set in zhTW and EN. - [KSmart/chinese_traditional_chengyu](https://huggingface.co/datasets/KSmart/chinese_traditional_chengyu): Translated from zhCN to zhTW using OpenCC (s2tw.json). - [zetavg/coct-en-zh-tw-translations-twp-300k](https://huggingface.co/datasets/zetavg/coct-en-zh-tw-translations-twp-300k): Formed instruction tuning pairs using zhTW and EN paired paragraphs. - [Heng666/Traditional_Chinese-aya_dataset](https://huggingface.co/datasets/Heng666/Traditional_Chinese-aya_dataset)

talalmuzaffar/empathetic_dataset_with_context

talalmuzaffar

--- dataset_info: features: - name: Context dtype: string - name: Input dtype: string - name: Response dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 1812315 num_examples: 8000 download_size: 964375 dataset_size: 1812315 configs: - config_name: default data_files: - split: train path: data/train-* ---

morten-j/medhie-tokenized-dataset-custom-bertwordpiece

morten-j

--- dataset_info: features: - name: input_ids sequence: int32 - name: token_type_ids sequence: int8 - name: attention_mask sequence: int8 - name: word_ids sequence: int64 - name: labels sequence: int64 splits: - name: train num_bytes: 42113819652 num_examples: 14830301 - name: validation num_bytes: 4836576832 num_examples: 1703172 download_size: 21646576639 dataset_size: 46950396484 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---

CCaccept/Subgraph

CCaccept

--- task_categories: - question-answering language: - en tags: - wikidata - freebase - KBQA - LLM - agent pretty_name: KG Subgraph size_categories: - 10K<n<100K --- # Subgraph Dataset ## Overview This repository contains a subgraph dataset associated with the subgraphs used in the paper [ODA: Observation-Driven Agent for integrating LLMs and Knowledge Graphs](https://arxiv.org/abs/2404.07677). For specific codes and the KBQA dataset, please refer to [KGdata repository](https://github.com/lanjiuqing64/KGdata.git). ## Description The dataset comprises four folders, each containing subgraphs related to different KBQA datasets based on Wikidata or Freebase: - Wikidata-based datasets: - QALD10-en - T-REx - Zero-Shot RE - Creak - Freebase-based datasets: - GrailQA - WebQSP - Simple Questions - `hop_2_FreeBase/`: Contains 2-hop subgraphs based on Freebase. - `hop_3_FreeBase/`: Contains 3-hop subgraphs based on Freebase. - `hop_2_Wikidata/`: Contains 2-hop subgraphs based on Wikidata. - `hop_3rd_Wikidata/`: Contains the third hop subgraphs based on Wikidata. ### The format of the subgraph files 1. FreeBase subgraph file ``` { Topic Entity : [[EntityID,Relation,EntityID],....], Topic Entity : [[EntityID,Relation,EntityID],....], ... } ``` 2. FreeBase label file ``` { EntityID : Entity name EntityID : Entity name ... } ``` 3. Wikidata subgraph file ``` { Topic Entity : [[EntityID,RelationID,EntityID],....], Topic Entity : [[EntityID,RelationID,EntityID],....], ... } ``` 2. Wikidata label file ``` { EntityID : Entity name RelationID : Relation name EntityID : Entity name ... } ```

phuctran75/buzzsentiment

phuctran75

--- license: llama3 ---

talalmuzaffar/empathetic_dataset_with_correct_context

talalmuzaffar

--- dataset_info: features: - name: Context dtype: string - name: Input dtype: string - name: Response dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 2567028 num_examples: 8000 download_size: 961982 dataset_size: 2567028 configs: - config_name: default data_files: - split: train path: data/train-* ---